ICPR2020 Paper Browser

Paper download is intended for registered attendees only, and is subjected to the IEEE Copyright Policy. Any other use is strongly forbidden.

Talking Face Generation Via Learning Semantic and Temporal Synchronous Landmarks

Aihua Zheng, Feixia Zhu, Hao Zhu, Mandi Luo, Ran He

Auto-TLDR; A semantic and temporal synchronous landmark learning method for talking face generation

Abstract Slides Poster

Abstract—Given a speech clip and facial image, the goal of talking face generation is to synthesize a talking face video with accurate mouth synchronization and natural face motion. Recent progress has proven the effectiveness of the landmarks as the intermediate information during talking face generation. However,the large gap between audio and visual modalities makes the prediction of landmarks challenging and limits generation ability. This paper proposes a semantic and temporal synchronous landmark learning method for talking face generation. First, we propose to introduce a word detector to enforce richer semantic information. Then, we propose to preserve the temporal synchronization and consistency between landmarks and audio via the proposed temporal residual loss. Lastly, we employ a U-Net generation network with adaptive reconstruction loss to generate facial images for the predicted landmarks. Experimental results on two benchmark datasets LRW and GRID demonstrate the effectiveness of our model compared to the state-of-the-art methods of talking face generation.

Similar papers

Let's Play Music: Audio-Driven Performance Video Generation

Hao Zhu, Yi Li, Feixia Zhu, Aihua Zheng, Ran He

Auto-TLDR; APVG: Audio-driven Performance Video Generation Using Structured Temporal UNet

Abstract Slides Poster Similar

We propose a new task named Audio-driven Performance Video Generation (APVG), which aims to synthesize the video of a person playing a certain instrument guided by a given music audio clip. It is a challenging task to generate the high-dimensional temporal consistent videos from low-dimensional audio modality. In this paper, we propose a multi-staged framework to achieve this new task to generate realistic and synchronized performance video from given music. Firstly, we provide both global appearance and local spatial information by generating the coarse videos and keypoints of body and hands from a given music respectively. Then, we propose to transform the generated keypoints to heatmap via a differentiable space transformer, since the heatmap offers more spatial information but is harder to generate directly from audio. Finally, we propose a Structured Temporal UNet (STU) to extract both intra-frame structured information and inter-frame temporal consistency. They are obtained via graph-based structure module, and CNN-GRU based high-level temporal module respectively for final video generation. Comprehensive experiments validate the effectiveness of our proposed framework.

A Neural Lip-Sync Framework for Synthesizing Photorealistic Virtual News Anchors

Ruobing Zheng, Zhou Zhu, Bo Song, Ji Changjiang

Auto-TLDR; Lip-sync: Synthesis of a Virtual News Anchor for Low-Delayed Applications

Abstract Slides Poster Similar

Lip sync has emerged as a promising technique to generate mouth movements from audio signals. However, synthesizing a high-resolution and photorealistic virtual news anchor with current methods is still challenging. The lack of natural appearance, visual consistency, and processing efficiency is the main issue. In this paper, we present a novel lip-sync framework specially designed for producing a virtual news anchor for a target person. A pair of Temporal Convolutional Networks are used to learn the seq-to-seq mapping from audio signals to mouth movements, followed by a neural rendering model that translates the intermediate face representation to the high-quality appearance. This fully-trainable framework avoids several time-consuming steps in traditional graphics-based methods, meeting the requirements of many low-delay applications. Experiments show that our method has advantages over modern neural-based methods in both visual appearance and processing efficiency.

Learning Disentangled Representations for Identity Preserving Surveillance Face Camouflage

Jingzhi Li, Lutong Han, Hua Zhang, Xiaoguang Han, Jingguo Ge, Xiaochu Cao

Auto-TLDR; Individual Face Privacy under Surveillance Scenario with Multi-task Loss Function

Abstract Poster Similar

In this paper, we focus on protecting the person face privacy under the surveillance scenarios, whose goal is to change the visual appearances of faces while keep them to be recognizable by current face recognition systems. This is a challenging problem as that we should retain the most important structures of captured facial images, while alter the salient facial regions to protect personal privacy. To address this problem, we introduce a novel individual face protection model, which can camouflage the face appearance from the perspective of human visual perception and preserve the identity features of faces used for face authentication. To that end, we develop an encoder-decoder network architecture that can separately disentangle the person feature representation into an appearance code and an identity code. Specifically, we first randomly divide the face image into two groups, the source set and the target set, where the source set is used to extract the identity code and the target set provides the appearance code. Then, we recombine the identity and appearance codes to synthesize a new face, which has the same identity with the source subject. Finally, the synthesized faces are used to replace the original face to protect the privacy of individual. Furthermore, our model is trained end-to-end with a multi-task loss function, which can better preserve the identity and stabilize the training loss. Experiments conducted on Cross-Age Celebrity dataset demonstrate the effectiveness of our model and validate our superiority in terms of visual quality and scalability.

Cascade Attention Guided Residue Learning GAN for Cross-Modal Translation

Bin Duan, Wei Wang, Hao Tang, Hugo Latapie, Yan Yan

Auto-TLDR; Cascade Attention-Guided Residue GAN for Cross-modal Audio-Visual Learning

Abstract Slides Poster Similar

Since we were babies, we intuitively develop the ability to correlate the input from different cognitive sensors such as vision, audio, and text. However, in machine learning, this cross-modal learning is a nontrivial task because different modalities have no homogeneous properties. Previous works discover that there should be bridges among different modalities. From neurology and psychology perspective, humans have the capacity to link one modality with another one, e.g., associating a picture of a bird with the only hearing of its singing and vice versa. Is it possible for machine learning algorithms to recover the scene given the audio signal? In this paper, we propose a novel Cascade Attention-Guided Residue GAN (CAR-GAN), aiming at reconstructing the scenes given the corresponding audio signals. Particularly, we present a residue module to mitigate the gap between different modalities progressively. Moreover, a cascade attention guided network with a novel classification loss function is designed to tackle the cross-modal learning task. Our model keeps consistency in the high-level semantic label domain and is able to balance two different modalities. The experimental results demonstrate that our model achieves the state-of-the-art cross-modal audio-visual generation on the challenging Sub-URMP dataset.

Unsupervised Contrastive Photo-To-Caricature Translation Based on Auto-Distortion

Yuhe Ding, Xin Ma, Mandi Luo, Aihua Zheng, Ran He

Auto-TLDR; Unsupervised contrastive photo-to-caricature translation with style loss

Abstract Slides Poster Similar

Photo-to-caricature aims to synthesize the caricature as a rendered image exaggerating the features through sketching, pencil strokes, or other artistic drawings. Style rendering and geometry deformation are the most important aspects in photo-to-caricature translation task. To take both into consideration, we propose an unsupervised contrastive photo-to-caricature translation architecture. Considering the intuitive artifacts in the existing methods, we propose a contrastive style loss for style rendering to enforce the similarity between the style of rendered photo and the caricature, and simultaneously enhance its discrepancy to the photos. To obtain an exaggerating deformation in an unpaired/unsupervised fashion, we propose a Distortion Prediction Module (DPM) to predict a set of displacements vectors for each input image while fixing some controlling points, followed by the thin plate spline interpolation for warping. The model is trained on unpaired photo and caricature while can offer bidirectional synthesizing via inputting either a photo or a caricature. Extensive experiments demonstrate that the proposed model is effective to generate hand-drawn like caricatures compared with existing competitors.

Coherence and Identity Learning for Arbitrary-Length Face Video Generation

Shuquan Ye, Chu Han, Jiaying Lin, Guoqiang Han, Shengfeng He

Auto-TLDR; Face Video Synthesis Using Identity-Aware GAN and Face Coherence Network

Abstract Slides Poster Similar

Face synthesis is an interesting yet challenging task in computer vision. It is even much harder to generate a portrait video than a single image. In this paper, we propose a novel video generation framework for synthesizing arbitrary-length face videos without any face exemplar or landmark. To overcome the synthesis ambiguity of face video, we propose a divide-and-conquer strategy to separately address the video face synthesis problem from two aspects, face identity synthesis and rearrangement. To this end, we design a cascaded network which contains three components, Identity-aware GAN (IA-GAN), Face Coherence Network, and Interpolation Network. IA-GAN is proposed to synthesize photorealistic faces with the same identity from a set of noises. Face Coherence Network is designed to re-arrange the faces generated by IA-GAN while keeping the inter-frame coherence. Interpolation Network is introduced to eliminate the discontinuity between two adjacent frames and improve the smoothness of the face video. Experimental results demonstrate that our proposed network is able to generate face video with high visual quality while preserving the identity. Statistics show that our method outperforms state-of-the-art unconditional face video generative models in multiple challenging datasets.

Dual-MTGAN: Stochastic and Deterministic Motion Transfer for Image-To-Video Synthesis

Fu-En Yang, Jing-Cheng Chang, Yuan-Hao Lee, Yu-Chiang Frank Wang

Auto-TLDR; Dual Motion Transfer GAN for Convolutional Neural Networks

Abstract Slides Poster Similar

Generating videos with content and motion variations is a challenging task in computer vision. While the recent development of GAN allows video generation from latent representations, it is not easy to produce videos with particular content of motion patterns of interest. In this paper, we propose Dual Motion Transfer GAN (Dual-MTGAN), which takes image and video data as inputs while learning disentangled content and motion representations. Our Dual-MTGAN is able to perform deterministic motion transfer and stochastic motion generation. Based on a given image, the former preserves the input content and transfers motion patterns observed from another video sequence, and the latter directly produces videos with plausible yet diverse motion patterns based on the input image. The proposed model is trained in an end-to-end manner, without the need to utilize pre-defined motion features like pose or facial landmarks. Our quantitative and qualitative results would confirm the effectiveness and robustness of our model in addressing such conditioned image-to-video tasks.

The Role of Cycle Consistency for Generating Better Human Action Videos from a Single Frame

Runze Li, Bir Bhanu

Auto-TLDR; Generating Videos with Human Action Semantics using Cycle Constraints

Abstract Slides Poster Similar

This paper addresses the challenging problem of generating videos with human action semantics. Unlike previous work which predict future frames in a single forward pass, this paper introduces the cycle constraints in both forward and backward passes in the generation of human actions. This is achieved by enforcing the appearance and motion consistency across a sequence of frames generated in the future. The approach consists of two stages. In the first stage, the pose of a human body is generated. In the second stage, an image generator is used to generate future frames by using (a) generated human poses in the future from the first stage, (b) the single observed human pose, and (c) the single corresponding future frame. The experiments are performed on three datasets: Weizmann dataset involving simple human actions, Penn Action dataset and UCF-101 dataset containing complicated human actions, especially in sports. The results from these experiments demonstrate the effectiveness of the proposed approach.

Exemplar Guided Cross-Spectral Face Hallucination Via Mutual Information Disentanglement

Haoxue Wu, Huaibo Huang, Aijing Yu, Jie Cao, Zhen Lei, Ran He

Auto-TLDR; Exemplar Guided Cross-Spectral Face Hallucination with Structural Representation Learning

Abstract Slides Poster Similar

Recently, many Near infrared-visible (NIR-VIS) heterogeneous face recognition (HFR) methods have been proposed in the community. But it remains a challenging problem because of the sensing gap along with large pose variations. In this paper, we propose an Exemplar Guided Cross-Spectral Face Hallucination (EGCH) to reduce the domain discrepancy through disentangled representation learning. For each modality, EGCH contains a spectral encoder as well as a structure encoder to disentangle spectral and structure representation, respectively. It also contains a traditional generator that reconstructs the input from the above two representations, and a structure generator that predicts the facial parsing map from the structure representation. Besides, mutual information minimization and maximization are conducted to boost disentanglement and make representations adequately expressed. Then the translation is built on structure representations between two modalities. Provided with the transformed NIR structure representation and original VIS spectral representation, EGCH is capable to produce high-fidelity VIS images that preserve the topology structure of the input NIR while transfer the spectral information of an arbitrary VIS exemplar. Extensive experiments demonstrate that the proposed method achieves more promising results both qualitatively and quantitatively than the state-of-the-art NIR-VIS methods.

Future Urban Scenes Generation through Vehicles Synthesis

Alessandro Simoni, Luca Bergamini, Andrea Palazzi, Simone Calderara, Rita Cucchiara

Auto-TLDR; Predicting the Future of an Urban Scene with a Novel View Synthesis Paradigm

Abstract Slides Poster Similar

In this work we propose a deep learning pipeline to predict the visual future appearance of an urban scene. Despite recent advances, generating the entire scene in an end-to-end fashion is still far from being achieved. Instead, here we follow a two stages approach, where interpretable information is included in the loop and each actor is modelled independently. We leverage a per-object novel view synthesis paradigm; i.e. generating a synthetic representation of an object undergoing a geometrical roto-translation in the 3D space. Our model can be easily conditioned with constraints (e.g. input trajectories) provided by state-of-the-art tracking methods or by the user itself. This allows us to generate a set of diverse realistic futures starting from the same input in a multi-modal fashion. We visually and quantitatively show the superiority of this approach over traditional end-to-end scene-generation methods on CityFlow, a challenging real world dataset.

Learning Visual Voice Activity Detection with an Automatically Annotated Dataset

Stéphane Lathuiliere, Pablo Mesejo, Radu Horaud

Auto-TLDR; Deep Visual Voice Activity Detection with Optical Flow

Abstract Slides Similar

Visual voice activity detection (V-VAD) uses visual features to predict whether a person is speaking or not. V-VAD is useful whenever audio VAD (A-VAD) is inefficient either because the acoustic signal is difficult to analyze or is simply missing. We propose two deep architectures for V-VAD, one based on facial landmarks and one based on optical flow. Moreover, available datasets, used for learning and for testing V-VAD, lack content variability. We introduce a novel methodology to automatically create and annotate very large datasets in-the-wild, based on combining A-VAD and face detection. A thorough empirical evaluation shows the advantage of training the proposed deep V-VAD models with such a dataset.

Unsupervised Face Manipulation Via Hallucination

Keerthy Kusumam, Enrique Sanchez, Georgios Tzimiropoulos

Auto-TLDR; Unpaired Face Image Manipulation using Autoencoders

Abstract Slides Poster Similar

This paper addresses the problem of manipulatinga face image in terms of changing its pose. To achieve this, wepropose a new method that can be trained under the very general“unpaired” setting. To this end, we firstly propose to modelthe general appearance, layout and background of the inputimage using a low-resolution version of it which is progressivelypassed through a hallucination network to generate featuresat higher resolutions. We show that such a formulation issignificantly simpler than previous approaches for appearancemodelling based on autoencoders. Secondly, we propose a fullylearnable and spatially-aware appearance transfer module whichcan cope with misalignment between the input source image andthe target pose and can effectively combine the features fromthe hallucination network with the features produced by ourgenerator. Thirdly, we introduce an identity preserving methodthat is trained in an unsupervised way, by using an auxiliaryfeature extractor and a contrastive loss between the real andgenerated images. We compare our method against the state-of-the-art reporting significant improvements both quantitatively, interms of FID and IS, and qualitatively.

Three-Dimensional Lip Motion Network for Text-Independent Speaker Recognition

Jianrong Wang, Tong Wu, Shanyu Wang, Mei Yu, Qiang Fang, Ju Zhang, Li Liu

Auto-TLDR; Lip Motion Network for Text-Independent and Text-Dependent Speaker Recognition

Abstract Slides Poster Similar

Lip motion reflects behavior characteristics of speakers, and thus can be used as a new kind of biometrics in speaker recognition. In the literature, lots of works used two dimensional (2D) lip images to recognize speaker in a text-dependent context. However, 2D lip easily suffers from face orientations. To this end, in this work, we present a novel end-to-end 3D lip motion Network (3LMNet) by utilizing the sentence-level 3D lip motion (S3DLM) to recognize speakers in both the text-independent and text-dependent contexts. A novel regional feedback module (RFM) is proposed to explore attentions in different lip regions. Besides, prior knowledge of lip motion is investigated to complement RFM, where landmark-level and frame-level features are merged to form a better feature representation. Moreover, we present two methods, i.e., coordinate transformation and face posture correction to pre-process the LSD-AV dataset, which contains 68 speakers and 146 sentences per speaker. The evaluation results on this dataset demonstrate that our proposed 3LMNet is superior to the baseline models, i.e., LSTM, VGG-16 and ResNet-34, and outperforms the state-of-the-art using 2D lip image as well as the 3D face. The code of this work is released at https://github.com/wutong18/Three-Dimensional-Lip-Motion-Ne twork-for-Text-Independent-Speaker-Recognition.

Face Super-Resolution Network with Incremental Enhancement of Facial Parsing Information

Shuang Liu, Chengyi Xiong, Zhirong Gao

Auto-TLDR; Learning-based Face Super-Resolution with Incremental Boosting Facial Parsing Information

Abstract Slides Poster Similar

Recently, facial priors based face super-resolution (SR) methods have obtained significant performance gains in dealing with extremely degraded facial images, and facial priors have also been proved useful in facilitating the inference of face images. Based on this, how to fully fuse facial priors into deep features to improve face SR performance has attracted a major attention. In this paper, we propose a learning-based face SR approach with incremental boosting facial parsing information (IFPSR) for high-magnification of low-resolution faces. The proposed IFPSR method consists of three main parts: i) a three-stage parsing map embedded features upsampling network, in which image recovery and prior estimation processes are performed simultaneously and progressively to improve the image resolution; ii) a progressive training method and a joint facial attention and heatmap loss to obtain better facial attributes; iii) the channel attention strategy in residual dense blocks to adaptively learn facial features. Extensive experimental results show that compared with the state-of-the-art methods in terms of quantitative and qualitative metrics, our approach can achieve an outstanding balance between SR image quality and low network complexity.

Shape Consistent 2D Keypoint Estimation under Domain Shift

Levi Vasconcelos, Massimiliano Mancini, Davide Boscaini, Barbara Caputo, Elisa Ricci

Auto-TLDR; Deep Adaptation for Keypoint Prediction under Domain Shift

Abstract Slides Poster Similar

Recent unsupervised domain adaptation methods based on deep architectures have shown remarkable performance not only in traditional classification tasks but also in more complex problems involving structured predictions (e.g. semantic segmentation, depth estimation). Following this trend, in this paper we present a novel deep adaptation framework for estimating keypoints under \textit{domain shift}, i.e. when the training (\textit{source}) and the test (\textit{target}) images significantly differ in terms of visual appearance. Our method seamlessly combines three different components: feature alignment, adversarial training and self-supervision. Specifically, our deep architecture leverages from domain-specific distribution alignment layers to perform target adaptation at the feature level. Furthermore, a novel loss is proposed which combines an adversarial term for ensuring aligned predictions in the output space and a geometric consistency term which guarantees coherent predictions between a target sample and its perturbed version. Our extensive experimental evaluation conducted on three publicly available benchmarks shows that our approach outperforms state-of-the-art domain adaptation methods in the 2D keypoint prediction task.

Two-Stream Temporal Convolutional Network for Dynamic Facial Attractiveness Prediction

Nina Weng, Jiahao Wang, Annan Li, Yunhong Wang

Auto-TLDR; 2S-TCN: A Two-Stream Temporal Convolutional Network for Dynamic Facial Attractiveness Prediction

Abstract Slides Poster Similar

In the field of facial attractiveness prediction, while deep models using static pictures have shown promising results, little attention is paid to dynamic facial information, which is proven to be influential by psychological studies. Meanwhile, the increasing popularity of short video apps creates an enormous demand of facial attractiveness prediction from short video clips. In this paper, we target on the dynamic facial attractiveness prediction problem. To begin with, a large-scale video-based facial attractiveness prediction dataset (VFAP) with more than one thousand clips from TikTok is collected. A two-stream temporal convolutional network (2S-TCN) is then proposed to capture dynamic attractiveness feature from both facial appearance and landmarks. We employ attentive feature enhancement along with specially designed modality and temporal fusion strategies to better explore the temporal dynamics. Extensive experiments on the proposed VFAP dataset demonstrate that 2S-TCN has a distinct advantage over the state-of-the-art static prediction methods.

Mutual Information Based Method for Unsupervised Disentanglement of Video Representation

Aditya Sreekar P, Ujjwal Tiwari, Anoop Namboodiri

Auto-TLDR; MIPAE: Mutual Information Predictive Auto-Encoder for Video Prediction

Abstract Slides Poster Similar

Video Prediction is an interesting and challenging task of predicting future frames from a given set context frames that belong to a video sequence. Video prediction models have found prospective applications in Maneuver Planning, Health care, Autonomous Navigation and Simulation. One of the major challenges in future frame generation is due to the high dimensional nature of visual data. In this work, we propose Mutual Information Predictive Auto-Encoder (MIPAE) framework, that reduces the task of predicting high dimensional video frames by factorising video representations into content and low dimensional pose latent variables that are easy to predict. A standard LSTM network is used to predict these low dimensional pose representations. Content and the predicted pose representations are decoded to generate future frames. Our approach leverages the temporal structure of the latent generative factors of a video and a novel mutual information loss to learn disentangled video representations. We also propose a metric based on mutual information gap (MIG) to quantitatively access the effectiveness of disentanglement on DSprites and MPI3D-real datasets. MIG scores corroborate with the visual superiority of frames predicted by MIPAE. We also compare our method quantitatively on evaluation metrics LPIPS, SSIM and PSNR.

Reducing the Variance of Variational Estimates of Mutual Information by Limiting the Critic's Hypothesis Space to RKHS

Aditya Sreekar P, Ujjwal Tiwari, Anoop Namboodiri

Auto-TLDR; Mutual Information Estimation from Variational Lower Bounds Using a Critic's Hypothesis Space

Abstract Slides Similar

Mutual information (MI) is an information-theoretic measure of dependency between two random variables. Several methods to estimate MI, from samples of two random variables with unknown underlying probability distributions have been proposed in the literature. Recent methods realize parametric probability distributions or critic as a neural network to approximate unknown density ratios. The approximated density ratios are used to estimate different variational lower bounds of MI. While these methods provide reliable estimation when the true MI is low, they produce high variance estimates in cases of high MI. We argue that the high variance characteristic is due to the uncontrolled complexity of the critic's hypothesis space. In support of this argument, we use the data-driven Rademacher complexity of the hypothesis space associated with the critic's architecture to analyse generalization error bound of variational lower bound estimates of MI. In the proposed work, we show that it is possible to negate the high variance characteristics of these estimators by constraining the critic's hypothesis space to Reproducing Hilbert Kernel Space (RKHS), which corresponds to a kernel learned using Automated Spectral Kernel Learning (ASKL). By analysing the aforementioned generalization error bounds, we augment the overall optimisation objective with effective regularisation term. We empirically demonstrate the efficacy of this regularization in enforcing proper bias variance tradeoff on four variational lower bounds, namely NWJ, MINE, JS and SMILE.

Unsupervised Learning of Landmarks Based on Inter-Intra Subject Consistencies

Weijian Li, Haofu Liao, Shun Miao, Le Lu, Jiebo Luo

Auto-TLDR; Unsupervised Learning for Facial Landmark Discovery using Inter-subject Landmark consistencies

Abstract Slides Similar

We present a novel unsupervised learning approach to image landmark discovery by incorporating the inter-subject landmark consistencies on facial images. This is achieved via an inter-subject mapping module that transforms original subject landmarks based on an auxiliary subject-related structure. To recover from the transformed images back to the original subject, the landmark detector is forced to learn spatial locations that contain the consistent semantic meanings both for the paired intra-subject images and between the paired inter-subject images. Our proposed method is extensively evaluated on two public facial image datasets (MAFL, AFLW) with various settings. Experimental results indicate that our method can extract the consistent landmarks for both datasets and achieve better performances compared to the previous state-of-the-art methods quantitatively and qualitatively.

Free-Form Image Inpainting Via Contrastive Attention Network

Xin Ma, Xiaoqiang Zhou, Huaibo Huang, Zhenhua Chai, Xiaolin Wei, Ran He

Auto-TLDR; Self-supervised Siamese inference for image inpainting

Abstract Slides Similar

Most deep learning based image inpainting approaches adopt autoencoder or its variants to fill missing regions in images. Encoders are usually utilized to learn powerful representational spaces, which are important for dealing with sophisticated learning tasks. Specifically, in the image inpainting task, masks with any shapes can appear anywhere in images (i.e., free-form masks) forming complex patterns. It is difficult for encoders to capture such powerful representations under this complex situation. To tackle this problem, we propose a self-supervised Siamese inference network to improve the robustness and generalization. Moreover, the restored image usually can not be harmoniously integrated into the exiting content, especially in the boundary area. To address this problem, we propose a novel Dual Attention Fusion module (DAF), which can combine both the restored and known regions in a smoother way and be inserted into decoder layers in a plug-and-play way. DAF is developed to not only adaptively rescale channel-wise features by taking interdependencies between channels into account but also force deep convolutional neural networks (CNNs) focusing more on unknown regions. In this way, the unknown region will be naturally filled from the outside to the inside. Qualitative and quantitative experiments on multiple datasets, including facial and natural datasets (i.e., Celeb-HQ, Pairs Street View, Places2 and ImageNet), demonstrate that our proposed method outperforms against state-of-the-arts in generating high-quality inpainting results.

Multi-Laplacian GAN with Edge Enhancement for Face Super Resolution

Shanlei Ko, Bi-Ru Dai

Auto-TLDR; Face Image Super-Resolution with Enhanced Edge Information

Abstract Slides Poster Similar

Face image super-resolution has become a research hotspot in the field of image processing. Nowadays, more and more researches add additional information, such as landmark, identity, to reconstruct high resolution images from low resolution ones, and have a good performance in quantitative terms and perceptual quality. However, these additional information is hard to obtain in many cases. In this work, we focus on reconstructing face images by extracting useful information from face images directly rather than using additional information. By observing edge information in each scale of face images, we propose a method to reconstruct high resolution face images with enhanced edge information. In additional, with the proposed training procedure, our method reconstructs photo-realistic images in upscaling factor 8x and outperforms state-of-the-art methods both in quantitative terms and perceptual quality.

Learning Semantic Representations Via Joint 3D Face Reconstruction and Facial Attribute Estimation

Zichun Weng, Youjun Xiang, Xianfeng Li, Juntao Liang, Wanliang Huo, Yuli Fu

Auto-TLDR; Joint Framework for 3D Face Reconstruction with Facial Attribute Estimation

Abstract Slides Poster Similar

We propose a novel joint framework for 3D face reconstruction (3DFR) that integrates facial attribute estimation (FAE) as an auxiliary task. One of the essential problems of 3DFR is to extract semantic facial features (e.g., Big Nose, High Cheekbones, and Asian) from in-the-wild 2D images, which is inherently involved with FAE. These two tasks, though heterogeneous, are highly relevant to each other. To achieve this, we leverage a Convolutional Neural Network to extract shared facial representations for both shape decoder and attribute classifier. We further develop an in-batch hybrid-task training scheme that enables our model to learn from heterogeneous facial datasets jointly within a mini-batch. Thanks to the joint loss that provides supervision from both 3DFR and FAE domains, our model learns the correlations between 3D shapes and facial attributes, which benefit both feature extraction and shape inference. Quantitative evaluation and qualitative visualization results confirm the effectiveness and robustness of our joint framework.

Unsupervised 3D Human Pose Estimation in Multi-view-multi-pose Video

Cheng Sun, Diego Thomas, Hiroshi Kawasaki

Auto-TLDR; Unsupervised 3D Human Pose Estimation from 2D Videos Using Generative Adversarial Network

Abstract Slides Poster Similar

3D human pose estimation from a single 2D video is an extremely difficult task because computing 3D geometry from 2D images is an ill-posed problem. Recent popular solutions adopt fully-supervised learning strategy, which requires to train a deep network on a large-scale ground truth dataset of 3D poses and 2D images. However, such a large-scale dataset with natural images does not exist, which limits the usability of existing methods. While building a complete 3D dataset is tedious and expensive, abundant 2D in-the-wild data is already publicly available. As a consequence, there is a growing interest in the computer vision community to design efficient techniques that use the unsupervised learning strategy, which does not require any ground truth 3D data. Such methods can be trained with only natural 2D images of humans. In this paper we propose an unsupervised method for estimating 3D human pose in videos. The standard approach for unsupervised learning is to use the Generative Adversarial Network (GAN) framework. To improve the performance of 3D human pose estimation in videos, we propose a new GAN network that enforces body consistency over frames in a video. We evaluate the efficiency of our proposed method on a public 3D human body dataset.

Attributes Aware Face Generation with Generative Adversarial Networks

Zheng Yuan, Jie Zhang, Shiguang Shan, Xilin Chen

Auto-TLDR; AFGAN: A Generative Adversarial Network for Attributes Aware Face Image Generation

Abstract Slides Poster Similar

Recent studies have shown remarkable success in face image generations. However, most of the existing methods only generate face images from random noise, and cannot generate face images according to the specific attributes. In this paper, we focus on the problem of face synthesis from attributes, which aims at generating faces with specific characteristics corresponding to the given attributes. To this end, we propose a novel attributes aware face image generator method with generative adversarial networks called AFGAN. Specifically, we firstly propose a two-path embedding layer and self-attention mechanism to convert binary attribute vector to rich attribute features. Then three stacked generators generate 64 * 64, 128 * 128 and 256 * 256 resolution face images respectively by taking the attribute features as input. In addition, an image-attribute matching loss is proposed to enhance the correlation between the generated images and input attributes. Extensive experiments on CelebA demonstrate the superiority of our AFGAN in terms of both qualitative and quantitative evaluations.

Joint Face Alignment and 3D Face Reconstruction with Efficient Convolution Neural Networks

Keqiang Li, Huaiyu Wu, Xiuqin Shang, Zhen Shen, Gang Xiong, Xisong Dong, Bin Hu, Fei-Yue Wang

Auto-TLDR; Mobile-FRNet: Efficient 3D Morphable Model Alignment and 3D Face Reconstruction from a Single 2D Facial Image

Abstract Slides Poster Similar

3D face reconstruction from a single 2D facial image is a challenging and concerned problem. Recent methods based on CNN typically aim to learn parameters of 3D Morphable Model (3DMM) from 2D images to render face alignment and 3D face reconstruction. Most algorithms are designed for faces with small, medium yaw angles, which is extremely challenging to align faces in large poses. At the same time, they are not efficient usually. The main challenge is that it takes time to determine the parameters accurately. In order to address this challenge with the goal of improving performance, this paper proposes a novel and efficient end-to-end framework. We design an efficient and lightweight network model combined with Depthwise Separable Convolution and Muti-scale Representation, Lightweight Attention Mechanism, named Mobile-FRNet. Simultaneously, different loss functions are used to constrain and optimize 3DMM parameters and 3D vertices during training to improve the performance of the network. Meanwhile, extensive experiments on the challenging datasets show that our method significantly improves the accuracy of face alignment and 3D face reconstruction. The model parameters and complexity of our method are also improved greatly.

Hybrid Approach for 3D Head Reconstruction: Using Neural Networks and Visual Geometry

Oussema Bouafif, Bogdan Khomutenko, Mohammed Daoudi

Auto-TLDR; Recovering 3D Head Geometry from a Single Image using Deep Learning and Geometric Techniques

Abstract Slides Poster Similar

Recovering the 3D geometric structure of a face from a single input image is a challenging active research area in computer vision. In this paper, we present a novel method for reconstructing 3D heads from a single or multiple image(s) using a hybrid approach based on deep learning and geometric techniques. We propose an encoder-decoder network based on the U-net architecture and trained on synthetic data only. It predicts both pixel-wise normal vectors and landmarks maps from a single input photo. Landmarks are used for the pose computation and the initialization of the optimization problem, which, in turn, reconstructs the 3D head geometry by using a parametric morphable model and normal vector fields. State-of-the-art results are achieved through qualitative and quantitative evaluation tests on both single and multi-view settings. Despite the fact that the model was trained only on synthetic data, it successfully recovers 3D geometry and precise poses for real-world images.

High Resolution Face Age Editing

Xu Yao, Gilles Puy, Alasdair Newson, Yann Gousseau, Pierre Hellier

Auto-TLDR; An Encoder-Decoder Architecture for Face Age editing on High Resolution Images

Abstract Slides Poster Similar

Face age editing has become a crucial task in film post-production, and is also becoming popular for general purpose photography. Recently, adversarial training has produced some of the most visually impressive results for image manipulation, including the face aging/de-aging task. In spite of considerable progress, current methods often present visual artifacts and can only deal with low-resolution images. In order to achieve aging/de-aging with the high quality and robustness necessary for wider use, these problems need to be addressed. This is the goal of the present work. We present an encoder-decoder architecture for face age editing. The core idea of our network is to encode a face image to age-invariant features, and learn a modulation vector corresponding to a target age. We then combine these two elements to produce a realistic image of the person with the desired target age. Our architecture is greatly simplified with respect to other approaches, and allows for fine-grained age editing on high resolution images in a single unified model. Source codes are available at https://github.com/InterDigitalInc/HRFAE.

Robust Audio-Visual Speech Recognition Based on Hybrid Fusion

Hong Liu, Wenhao Li, Bing Yang

Auto-TLDR; Hybrid Fusion Based AVSR with Residual Networks and Bidirectional Gated Recurrent Unit for Robust Speech Recognition in Noise Conditions

Abstract Slides Poster Similar

The fusion of audio and visual modalities is an important stage of audio-visual speech recognition (AVSR), which is generally approached through feature fusion or decision fusion. Feature fusion can exploit the covariations between features from different modalities effectively, whereas decision fusion shows the robustness of capturing an optimal combination of multi-modality. In this work, to take full advantage of the complementarity of the two fusion strategies and address the challenge of inherent ambiguity in noisy environments, we propose a novel hybrid fusion based AVSR method with residual networks and Bidirectional Gated Recurrent Unit (BGRU), which is able to distinguish homophones in both clean and noisy conditions. Specifically, a simple yet effective audio-visual encoder is used to map audio and visual features into a shared latent space to capture more discriminative multi-modal feature and find the internal correlation between spatial-temporal information for different modalities. Furthermore, a decision fusion module is designed to get final predictions in order to robustly utilize the reliability measures of audio-visual information. Finally, we introduce a combined loss, which shows its noise-robustness in learning the joint representation across various modalities. Experimental results on the largest publicly available dataset (LRW) demonstrate the robustness of the proposed method under various noisy conditions.

Local-Global Interactive Network for Face Age Transformation

Jie Song, Ping Wei, Huan Li, Yongchi Zhang, Nanning Zheng

Auto-TLDR; A Novel Local-Global Interaction Framework for Long-span Face Age Transformation

Abstract Slides Poster Similar

Face age transformation, which aims to generate a face image in the past or future, has receiving increasing attention due to its significant application value in some special fields, such as looking for a lost child, tracking criminals and entertainment, etc. Currently, most existing methods mainly focus on unidirectional short-span face aging. In this paper, we propose a novel local-global interaction framework for long-span face age transformation. Firstly, we divide a face image into five independent parts and design a local generative network for each of them to learn the local structure changes of a face image, while we utilize a global generative network to learn the global structure changes. Then we introduce an interactive network and an age classification network, which are respectively used to integrate the local and global features and maintain the corresponding age features in different age groups. Given any face image at a certain age, our network can produce a clear and realistic image of face aging or rejuvenation. We test and evaluate the model on complex datasets, and extensive qualitative comparison experiments has proved the effectiveness and immense potential of our proposed method.

Mutual Alignment between Audiovisual Features for End-To-End Audiovisual Speech Recognition

Hong Liu, Yawei Wang, Bing Yang

Auto-TLDR; Mutual Iterative Attention for Audio Visual Speech Recognition

Abstract Slides Poster Similar

Asynchronization issue caused by different types of modalities is one of the major problems in audio visual speech recognition (AVSR) research. However, most AVSR systems merely rely on up sampling of video or down sampling of audio to align audio and visual features, assuming that the feature sequences are aligned frame-by-frame. These pre-processing steps oversimplify the asynchrony relation between acoustic signal and lip motion, lacking ﬂexibility and impairing the performance of the system. Although there are systems modeling the asynchrony between the modalities, sometimes they fail to align speech and video precisely in some even all noise conditions. In this paper, we propose a mutual feature alignment method for AVSR which can make full use of cross modility information to address the asynchronization issue by introducing Mutual Iterative Attention (MIA) mechanism. Our method can automatically learn an alignment in a mutual way by performing mutual attention iteratively between the audio and visual features, relying on the modified encoder structure of Transformer. Experimental results show that our proposed method obtains absolute improvements up to 20.42% over the audio modality alone depending upon the signal-to-noise-ratio (SNR) level. Better recognition performance can also be achieved comparing with the traditional feature concatenation method under both clean and noisy conditions. It is expectable that our proposed mutual feature alignment method can be easily generalized to other multimodal tasks with semantically correlated information.

Multi-Attribute Regression Network for Face Reconstruction

Xiangzheng Li, Suping Wu

Auto-TLDR; A Multi-Attribute Regression Network for Face Reconstruction

Abstract Slides Poster Similar

In this paper, we propose a multi-attribute regression network (MARN) to investigate the problem of face reconstruction, especially in challenging cases when faces undergo large variations including severe poses, extreme expressions, and partial occlusions in unconstrained environments. The traditional 3DMM parametric regression method is absent from the learning of identity, expression, and attitude attributes, resulting in lacking geometric details in the reconstructed face. Our MARN method is to enable the network to better extract the feature information of face identity, expression, and pose attributes. We introduced identity, expression, and pose attribute loss functions to enhance the learning of details in each attribute. At the same time, we carefully design the geometric contour constraint loss function and use the constraints of sparse 2D face landmarks to improve the reconstructed geometric contour information. The experimental results show that our face reconstruction method has achieved significant results on the AFLW2000-3D and AFLW datasets compared with the most advanced methods. In addition, there has been a great improvement in dense face alignment. .

Continuous Learning of Face Attribute Synthesis

Ning Xin, Shaohui Xu, Fangzhe Nan, Xiaoli Dong, Weijun Li, Yuanzhou Yao

Auto-TLDR; Continuous Learning for Face Attribute Synthesis

Abstract Slides Poster Similar

The generative adversarial network (GAN) exhibits great superiority in the face attribute synthesis task. However, existing methods have very limited effects on the expansion of new attributes. To overcome the limitations of a single network in new attribute synthesis, a continuous learning method for face attribute synthesis is proposed in this work. First, the feature vector of the input image is extracted and attribute direction regression is performed in the feature space to obtain the axes of different attributes. The feature vector is then linearly guided along the axis so that images with target attributes can be synthesized by the decoder. Finally, to make the network capable of continuous learning, the orthogonal direction modification module is used to extend the newly-added attributes. Experimental results show that the proposed method can endow a single network with the ability to learn attributes continuously, and, as compared to those produced by the current state-of-the-art methods, the synthetic attributes have higher accuracy.

SATGAN: Augmenting Age Biased Dataset for Cross-Age Face Recognition

Wenshuang Liu, Wenting Chen, Yuanlue Zhu, Linlin Shen

Auto-TLDR; SATGAN: Stable Age Translation GAN for Cross-Age Face Recognition

Abstract Slides Poster Similar

In this paper, we propose a Stable Age Translation GAN (SATGAN) to generate fake face images at different ages to augment age biased face datasets for Cross-Age Face Recognition (CAFR) . The proposed SATGAN consists of both generator and discriminator. As a part of the generator, a novel Mask Attention Module (MAM) is introduced to make the generator focus on the face area. In addition, the generator employs a Uniform Distribution Discriminator (UDD) to supervise the learning of latent feature map and enforce the uniform distribution. Besides, the discriminator employs a Feature Separation Module (FSM) to disentangle identity information from the age information. The quantitative and qualitative evaluations on Morph dataset prove that SATGAN achieves much better performance than existing methods. The face recognition model trained using dataset (VGGFace2 and MS-Celeb-1M) augmented using our SATGAN achieves better accuracy on cross age dataset like Cross-Age LFW and AgeDB-30.

Motion-Supervised Co-Part Segmentation

Aliaksandr Siarohin, Subhankar Roy, Stéphane Lathuiliere, Sergey Tulyakov, Elisa Ricci, Nicu Sebe

Auto-TLDR; Self-supervised Co-Part Segmentation Using Motion Information from Videos

Abstract Slides Similar

Recent co-part segmentation methods mostly operate in a supervised learning setting, which requires a large amount of annotated data for training. To overcome this limitation, we propose a self-supervised deep learning method for co-part segmentation. Differently from previous works, our approach develops the idea that motion information inferred from videos can be leveraged to discover meaningful object parts. To this end, our method relies on pairs of frames sampled from the same video. The network learns to predict part segments together with a representation of the motion between two frames, which permits reconstruction of the target image. Through extensive experimental evaluation on publicly available video sequences we demonstrate that our approach can produce improved segmentation maps with respect to previous self-supervised co-part segmentation approaches.

Contrastive Data Learning for Facial Pose and Illumination Normalization

Gee-Sern Hsu, Chia-Hao Tang

Auto-TLDR; Pose and Illumination Normalization with Contrast Data Learning for Face Recognition

Abstract Slides Poster Similar

Face normalization can be a crucial step when handling generic face recognition. We propose the Pose and Illumination Normalization (PIN) framework with contrast data learning for face normalization. The PIN framework is designed to learn the transformation from a source set to a target set. The source set and the target set compose a contrastive data set for learning. The source set contains faces collected in the wild and thus covers a wide range of variation across illumination, pose, expression and other variables. The target set contains face images taken under controlled conditions and all faces are in frontal pose and balanced in illumination. The PIN framework is composed of an encoder, a decoder and two discriminators. The encoder is made of a state-of-the-art face recognition network and acts as a facial feature extractor, which is not updated during training. The decoder is trained on both the source and target sets, and aims to learn the transformation from the source set to the target set; and therefore, it can transform an arbitrary face into a illumination and pose normalized face. The discriminators are trained to ensure the photo-realistic quality of the normalized face images generated by the decoder. The loss functions employed in the decoder and discriminators are appropriately designed and weighted for yielding better normalization outcomes and recognition performance. We verify the performance of the propose framework on several benchmark databases, and compare with state-of-the-art approaches.

Attentive Hybrid Feature Based a Two-Step Fusion for Facial Expression Recognition

Jun Weng, Yang Yang, Zichang Tan, Zhen Lei

Auto-TLDR; Attentive Hybrid Architecture for Facial Expression Recognition

Abstract Slides Poster Similar

Facial expression recognition is inherently a challenging task, especially for the in-the-wild images with various occlusions and large pose variations, which may lead to the loss of some crucial information. To address it, in this paper, we propose an attentive hybrid architecture (AHA) which learns global, local and integrated features based on different face regions. Compared with one type of feature, our extracted features own complementary information and can reduce the loss of crucial information. Specifically, AHA contains three branches, where all sub-networks in those branches employ the attention mechanism to further localize the interested pixels/regions. Moreover, we propose a two-step fusion strategy based on LSTM to deeply explore the hidden correlations among different face regions. Extensive experiments on four popular expression databases (i.e., CK+, FER-2013, SFEW 2.0, RAF-DB) show the effectiveness of the proposed method.

Unsupervised Disentangling of Viewpoint and Residues Variations by Substituting Representations for Robust Face Recognition

Minsu Kim, Joanna Hong, Junho Kim, Hong Joo Lee, Yong Man Ro

Auto-TLDR; Unsupervised Disentangling of Identity, viewpoint, and Residue Representations for Robust Face Recognition

Abstract Slides Poster Similar

It is well-known that identity-unrelated variations (e.g., viewpoint or illumination) degrade the performances of face recognition methods. In order to handle this challenge, a robust method for disentangling the identity and view representations has drawn an attention in the machine learning area. However, existing methods learn discriminative features which require a manual supervision of such factors of variations. In this paper, we propose a novel disentangling framework through modeling three representations of identity, viewpoint, and residues (i.e., identity and pose unrelated) which do not require supervision of the variations. By jointly modeling the three representations, we enhance the disentanglement of each representation and achieve robust face recognition performance. Further, the learned viewpoint representation can be utilized for pose estimation or editing of a posed facial image. Extensive quantitative and qualitative evaluations verify the effectiveness of our proposed method which disentangles identity, viewpoint, and residues of facial images.

GarmentGAN: Photo-Realistic Adversarial Fashion Transfer

Amir Hossein Raffiee, Michael Sollami

Auto-TLDR; GarmentGAN: A Generative Adversarial Network for Image-Based Garment Transfer

Abstract Slides Poster Similar

The garment transfer problem comprises two tasks: learning to separate a person's body (pose, shape, color) from their clothing (garment type, shape, style) and then generating new images of the wearer dressed in arbitrary garments. We present GarmentGAN, a new algorithm that performs image-based garment transfer through generative adversarial methods. The GarmentGAN framework allows users to virtually try-on items before purchase and generalizes to various apparel types. GarmentGAN requires as input only two images, namely, a picture of the target fashion item and an image containing the customer. The output is a synthetic image wherein the customer is wearing the target apparel. In order to make the generated image look photo-realistic, we employ the use of novel generative adversarial techniques. GarmentGAN improves on existing methods in the realism of generated imagery and solves various problems related to self-occlusions. Our proposed model incorporates additional information during training, utilizing both segmentation maps and body key-point information. We show qualitative and quantitative comparisons to several other networks to demonstrate the effectiveness of this technique.

Audio-Visual Predictive Coding for Self-Supervised Visual Representation Learning

Mani Kumar Tellamekala, Michel Valstar, Michael Pound, Timo Giesbrecht

Auto-TLDR; AV-PPC: A Multi-task Learning Framework for Learning Semantic Visual Features from Unlabeled Video Data

Abstract Slides Poster Similar

Self-supervised learning has emerged as a candidate approach to learn semantic visual features from unlabeled video data. In self-supervised learning, intrinsic correspondences between data points are used to define a proxy task that forces the model to learn semantic representations. Most existing proxy tasks applied to video data exploit only either intra-modal (e.g. temporal) or cross-modal (e.g. audio-visual) correspondences separately. In theory, jointly learning both these correspondences may result in richer visual features; but, as we show in this work, doing so is non-trivial in practice. To address this problem, we introduce `Audio-Visual Permutative Predictive Coding' (AV-PPC), a multi-task learning framework designed to fully leverage the temporal and cross-modal correspondences as natural supervision signals. In AV-PPC, the model is trained to simultaneously learn multiple intra- and cross-modal predictive coding sub-tasks. By using visual speech recognition (lip-reading) as the downstream evaluation task, we show that our proposed proxy task can learn higher quality visual features than existing proxy tasks. We also show that AV-PPC visual features are highly data-efficient. Without further finetuning, AV-PPC visual encoder achieves 80.30% spoken word classification rate on the LRW dataset, performing on par with directly or fully supervised visual encoders learned from large amounts of labeled data.

Boundary Guided Image Translation for Pose Estimation from Ultra-Low Resolution Thermal Sensor

Kohei Kurihara, Tianren Wang, Teng Zhang, Brian Carrington Lovell

Auto-TLDR; Pose Estimation on Low-Resolution Thermal Images Using Image-to-Image Translation Architecture

Abstract Slides Poster Similar

This work addresses the pose estimation task on low-resolution images captured using thermal sensors which can operate in a no-light environment. Low-resolution thermal sensors have been widely adopted in various applications for cost control and privacy protection purposes. In this paper, targeting the challenging scenario of ultra-low resolution thermal imaging (3232 pixels), we aim to estimate human poses for the purpose of monitoring health conditions and indoor events. To overcome the challenges in ultra-low resolution thermal imaging such as blurred boundaries and data scarcity, we propose a new Image-to-Image (I2I) translation architecture which can translate the original blurred thermal image into a visible light image with sharper boundaries. Then the generated visible light image can be fed into the off-the-shelf pose estimator which was well-trained in the visible domain. Experimental results suggest that the proposed framework outperforms other state-of-the-art methods in the I2I based pose estimation task for our thermal image dataset. Furthermore, we also demonstrated the merits of the proposed method on the publicly available FLIR dataset by measuring the quality of translated images.

Visual Oriented Encoder: Integrating Multimodal and Multi-Scale Contexts for Video Captioning

Bang Yang, Yuexian Zou

Auto-TLDR; Visual Oriented Encoder for Video Captioning

Abstract Slides Poster Similar

Video captioning is a challenging task which aims at automatically generating a natural language description of a given video. Recent researches have shown that exploiting the intrinsic multi-modalities of videos significantly promotes captioning performance. However, how to integrate multi-modalities to generate effective semantic representations for video captioning is still an open issue. Some researchers proposed to learn multimodal features in parallel during the encoding stage. The downside of these methods lies in the neglect of the interaction among multi-modalities and their rich contextual information. In this study, inspired by the fact that visual contents are generally more important for comprehending videos, we propose a novel Visual Oriented Encoder (VOE) to integrate multimodal features in an interactive manner. Specifically, VOE is designed as a hierarchical structure, where bottom layers are utilized to extract multi-scale contexts from auxiliary modalities while the top layer is exploited to generate joint representations by considering both visual and contextual information. Following the encoder-decoder framework, we systematically develop a VOE-LSTM model and evaluate it on two mainstream benchmarks: MSVD and MSR-VTT. Experimental results show that the proposed VOE surpasses conventional encoders and our VOE-LSTM model achieves competitive results compared with state-of-the-art approaches.

SIDGAN: Single Image Dehazing without Paired Supervision

Pan Wei, Xin Wang, Lei Wang, Ji Xiang, Zihan Wang

Auto-TLDR; DehazeGAN: An End-to-End Generative Adversarial Network for Image Dehazing

Abstract Slides Poster Similar

Single image dehazing is challenging without scene airlight and transmission map. Most of existing dehazing algorithms tend to estimate key parameters based on manual designed priors or statistics, which may be invalid in some scenarios. Although deep learning-based dehazing methods provide an effective solution, most of them rely on paired training datasets, which are prohibitively difficult to be collected in real world. In this paper, we propose an effective end-to-end generative adversarial network for image dehazing, named DehazeGAN. The proposed DehazeGAN adopts a U-net architecture with a novel color-consistency loss derived from dark channel prior and perceptual loss, which can be trained in an unsupervised fashion without paired synthetic datasets. We create a RealHaze dataset for network training, including 4,000 outdoor hazy images and 4,000 haze-free images. Extensive experiments demonstrate that our proposed DehazeGAN achieves better performance than existing state-of-the-art methods on both synthetic datasets and real-world datasets in terms of PSNR, SSIM, and subjective visual experience.

Self-Supervised Learning of Dynamic Representations for Static Images

Siyang Song, Enrique Sanchez, Linlin Shen, Michel Valstar

Auto-TLDR; Facial Action Unit Intensity Estimation and Affect Estimation from Still Images with Multiple Temporal Scale

Abstract Slides Poster Similar

Facial actions are spatio-temporal signals by nature, and therefore their modeling is crucially dependent on the availability of temporal information. In this paper, we focus on inferring such temporal dynamics of facial actions when no explicit temporal information is available, i.e. from still images. We present a novel approach to capture multiple scales of such temporal dynamics, with an application to facial Action Unit (AU) intensity estimation and dimensional affect estimation. In particular, 1) we propose a framework that infers a dynamic representation (DR) from a still image, which captures the bi-directional flow of time within a short time-window centered at the input image; 2) we show that we can train our method without the need of explicitly generating target representations, allowing the network to represent dynamics more broadly; and 3) we propose to apply a multiple temporal scale approach that infers DRs for different window lengths (MDR) from a still image. We empirically validate the value of our approach on the task of frame ranking, and show how our proposed MDR attains state of the art results on BP4D for AU intensity estimation and on SEMAINE for dimensional affect estimation, using only still images at test time.

A Multi-Task Neural Network for Action Recognition with 3D Key-Points

Rongxiao Tang, Wang Luyang, Zhenhua Guo

Auto-TLDR; Multi-task Neural Network for Action Recognition and 3D Human Pose Estimation

Abstract Slides Poster Similar

Action recognition and 3D human pose estimation are the fundamental problems in computer vision and closely related. In this work, we propose a multi-task neural network for action recognition and 3D human pose estimation. The results of the previous methods are still error-prone especially when tested against the images taken in-the-wild, leading error results in action recognition. To solve this problem, we propose a principled approach to generate high quality 3D pose ground truth given any in-the-wild image with a person inside. We achieve this by first devising a novel stereo inspired neural network to directly map any 2D pose to high quality 3D counterpart. Based on the high-quality 3D labels, we carefully design the multi-task framework for action recognition and 3D human pose estimation. The proposed architecture can utilize the shallow, deep features of the images, and the in-the-wild 3D human key-points to guide a more precise result. High quality 3D key-points can fully reflect the morphological features of motions, thus boosting the performance on action recognition. Experiments demonstrate that 3D pose estimation leads to significantly higher performance on action recognition than separated learning. We also evaluate the generalization ability of our method both quantitatively and qualitatively. The proposed architecture performs favorably against the baseline 3D pose estimation methods. In addition, the reported results on Penn Action and NTU datasets demonstrate the effectiveness of our method on the action recognition task.

Identity-Aware Facial Expression Recognition in Compressed Video

Xiaofeng Liu, Linghao Jin, Xu Han, Jun Lu, Jonghye Woo, Jane You

Auto-TLDR; Exploring Facial Expression Representation in Compressed Video with Mutual Information Minimization

Abstract Slides Similar

This paper targets to explore the inter-subject variations eliminated facial expression representation in the compressed video domain. Most of the previous methods process the RGB images of a sequence, while the off-the-shelf and valuable expression-related muscle movement already embedded in the compression format. In the up to two orders of magnitude compressed domain, we can explicitly infer the expression from the residual frames and possible to extract identity factors from the I frame with a pre-trained face recognition network. By enforcing the marginal independent of them, the expression feature is expected to be purer for the expression and be robust to identity shifts. Specifically, we propose a novel collaborative min-min game for mutual information (MI) minimization in latent space. We do not need the identity label or multiple expression samples from the same person for identity elimination. Moreover, when the apex frame is annotated in the dataset, the complementary constraint can be further added to regularize the feature-level game. In testing, only the compressed residual frames are required to achieve expression prediction. Our solution can achieve comparable or better performance than the recent decoded image based methods on the typical FER benchmarks with about 3$\times$ faster inference with compressed data.

Image Inpainting with Contrastive Relation Network

Xiaoqiang Zhou, Junjie Li, Zilei Wang, Ran He, Tieniu Tan

Auto-TLDR; Two-Stage Inpainting with Graph-based Relation Network

Abstract Slides Similar

Image inpainting faces the challenging issue of the requirements on structure reasonableness and texture coherence. In this paper, we propose a two-stage inpainting framework to address this issue. The basic idea is to address the two requirements in two separate stages. Completed segmentation of the corrupted image is firstly predicted through segmentation reconstruction network, while fine-grained image details are restored in the second stage through an image generator. The two stages are connected in series as the image details are generated under the guidance of completed segmentation map that predicted in the first stage. Specifically, in the second stage, we propose a novel graph-based relation network to model the relationship existed in corrupted image. In relation network, both intra-relationship for pixels in the same semantic region and inter-relationship between different semantic parts are considered, improving the consistency and compatibility of image textures. Besides, contrastive loss is designed to facilitate the relation network training. Such a framework not only simplifies the inpainting problem directly, but also exploits the relationship in corrupted image explicitly. Extensive experiments on various public datasets quantitatively and qualitatively demonstrate the superiority of our approach compared with the state-of-the-art.

What and How? Jointly Forecasting Human Action and Pose

Yanjun Zhu, Yanxia Zhang, Qiong Liu, Andreas Girgensohn

Auto-TLDR; Forecasting Human Actions and Motion Trajectories with Joint Action Classification and Pose Regression

Abstract Slides Poster Similar

Forecasting human actions and motion trajectories addresses the problem of predicting what a person is going to do next and how they will perform it. This is crucial in a wide range of applications such as assisted living and future co-robotic settings. We propose to simultaneously learn actions and action-related human motion dynamics, while existing works perform them independently. In this paper, we present a method to jointly forecast categories of human action and the pose of skeletal joints in the hope that the two tasks can help each other. As a result, our system can predict not only the future actions but also the motion trajectories that will result. To achieve this, we define a task of joint action classification and pose regression. We employ a sequence to sequence encoder-decoder model combined with multi-task learning to forecast future actions and poses progressively before the action happens. Experimental results on two public datasets, IkeaDB and OAD, demonstrate the effectiveness of the proposed method.

Residual Learning of Video Frame Interpolation Using Convolutional LSTM

Keito Suzuki, Masaaki Ikehara

Auto-TLDR; Video Frame Interpolation Using Residual Learning and Convolutional LSTMs

Abstract Slides Poster Similar

Video frame interpolation aims to generate interme- diate frames between the original frames. This produces videos with a higher frame r ate and creates smoother motion. Many video frame interpolation methods first estimate the motion vector between the input frames and then synthesizes the intermediate frame based on the motion. However, these methods rely on the accuracy of the motion estimation step and fail to accurately generate the interpolated frame when the estimated motion vectors are inaccurate. Therefore, to avoid the uncertainties caused by motion estimation, this paper proposes a method that directly generates the intermediate frame. Since two consecutive frames are relatively similar, our method takes the average of these two frames and utilizes residual learning to learn the difference between the average of these frames and the ground truth middle frame. In addition, our method uses Convolutional LSTMs and four input frames to better incorporate spatiotemporal information. This neural network can be easily trained end to end without difficult to obtain data such as optical flow. Our experimental results show that the proposed method can perform favorably against other state-of-the-art frame interpolation methods.