Reconstructing the underlying 3D surface of an object from a single image is a challenging problem that has received extensive attention from the computer vision community. Many learning-based approaches tackle this problem by learning a 3D shape prior from either ground truth 3D data or multi-view observations. To achieve state-of-the-art results, these methods assume that the objects are specified with respect to a fixed canonical coordinate frame, where instances of the same category are perfectly aligned. In this work, we present a new method for joint category-specific 3D reconstruction and object pose estimation from a single image. We show that one can leverage shape priors learned on purely synthetic 3D data together with a point cloud pose canonicalization method to achieve high-quality 3D reconstruction in the wild. Given a single depth image at test time, we first transform this partial point cloud into a learned canonical frame. Then, we use a neural deformation field to reconstruct the 3D surface of the object. Finally, we jointly optimize object pose and 3D shape to fit the partial depth observation. Our approach achieves state-of-the-art reconstruction performance across several real-world datasets, even when trained only on synthetic data. We further show that our method generalizes to different input modalities, from dense depth images to sparse and noisy LIDAR scans.
Uber Advanced Technologies Group（优步先进技术集团）；University of California, San Diego（加州大学圣迭戈分校）；University of Toronto（多伦多大学）
3D shape completion for real data is important but challenging, since partial point clouds acquired by real-world sensors are usually sparse, noisy and unaligned. Different from previous methods, we address the problem of learning 3D complete shape from unaligned and real-world partial point clouds. To this end, we propose a weakly-supervised method to estimate both 3D canonical shape and 6-DoF pose for alignment, given multiple partial observations associated with the same instance. The network jointly optimizes canonical shapes and poses with multi-view geometry constraints during training, …
Peking University（北京大学）；Beijing Institute for General AI（北京通用人工智能研究院）；Virginia Tech（弗吉尼亚理工大学）；Stanford University（斯坦福大学）；Tsinghua University（清华大学）；Columbia University（哥伦比亚大学）
In this work, we tackle the challenging task of jointly tracking hand object pose and reconstructing their shapes from depth point cloud sequences in the wild, given the initial poses at frame 0. We for the first time propose a point cloud based hand joint tracking network, HandTrackNet, to estimate the inter-frame hand joint motion. Our HandTrackNet proposes a novel hand pose canonicalization module to ease the tracking task, yielding accurate and robust hand joint tracking. Our pipeline then reconstructs the full hand via converting the predicted hand joints into a template-based parametric …
ETH Zürich（苏黎世联邦理工学院）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）
Capturing the dynamically deforming 3D shape of clothed human is essential for numerous applications, including VR/AR, autonomous driving, and human-computer interaction. Existing methods either require a highly specialized capturing setup, such as expensive multi-view imaging systems, or they lack robustness to challenging body poses. In this work, we propose a method capable of capturing the dynamic 3D human shape from a monocular video featuring challenging body poses, without any additional input. We first build a 3D template human model of the subject based on a learned regression model. …
Tsinghua University（清华大学）；USTC（中国科学技术大学）；Microsoft Research Asia（微软亚洲研究院）
This paper deals with the challenging task of synthesizing novel views for in-the-wild photographs. Existing methods have shown promising results leveraging monocular depth estimation and color inpainting with layered depth representations. However, these methods still have limited capability to handle scenes with complex 3D geometry. We propose a new method based on the multiplane image (MPI) representation. To accommodate diverse scene layouts in the wild and tackle the difficulty in producing high-dimensional MPI contents, we design a network structure that consists of two novel modules, on…
We demonstrate that it is possible to perform face-related computer vision in the wild using synthetic data alone. The community has long enjoyed the benefits of synthesizing training data with graphics, but the domain gap between real and synthetic data has remained a problem, especially for human faces. Researchers have tried to bridge this gap with data mixing, domain adaptation, and domain-adversarial training, but we show that it is possible to synthesize data with minimal domain gap, so that models trained on synthetic data generalize to real in-the-wild datasets. We describe how to comb…
Recently, counting the number of people for crowd scenes is a hot topic because of its widespread applications (e.g. video surveillance, public security). It is a difficult task in the wild: changeable environment, large-range number of people cause the current methods can not work well. In addition, due to the scarce data, many methods suffer from over-fitting to a different extent. To remedy the above two problems, firstly, we develop a data collector and labeler, which can generate the synthetic crowd scenes and simultaneously annotate them without any manpower. Based on it, we build a larg…
Xi’an Jiaotong University（西安交通大学）；Tencent AI Lab（腾讯人工智能实验室）
Neural Radiance Fields (NeRF) has recently gained popularity for its impressive novel view synthesis ability. This paper studies the problem of hallucinated NeRF: i.e., recovering a realistic NeRF at a different time of day from a group of tourism images. Existing solutions adopt NeRF with a controllable appearance embedding to render novel views under various conditions, but they cannot render view-consistent images with an unseen appearance. To solve this problem, we present an end-to-end framework for constructing a hallucinated NeRF, dubbed as Ha-NeRF. Specifically, we propose an appearanc…
Shanghai Jiao Tong University（上海交通大学）；Qing Yuan Research Institute（清源研究院）；AI Institute, Shanghai Jiao Tong University（上海交通大学人工智能研究院）；Shanghai Qi Zhi Institute（上海期智研究院）
In this paper, we tackle the problem of category-level 9D pose estimation in the wild, given a single RGB-D frame. Using supervised data of real-world 9D poses is tedious and erroneous, and also fails to generalize to unseen scenarios. Besides, category-level pose estimation requires a method to be able to generalize to unseen objects at test time, which is also challenging. Drawing inspirations from traditional point pair features (PPFs), in this paper, we design a novel Category-level PPF (CPPF) voting method to achieve accurate, robust and generalizable 9D pose estimation in the wild. To ob…
Robotics Institute, Carnegie Mellon University（卡内基梅隆大学机器人研究所）
Recent history has seen a tremendous growth of work exploring implicit representations of geometry and radiance, popularized through Neural Radiance Fields (NeRF). Such works are fundamentally based on a (implicit) volumetric representation of occupancy, allowing them to model diverse scene structure including translucent objects and atmospheric obscurants. But because the vast majority of real-world scenes are composed of well-defined surfaces, we introduce a surface analog of such implicit models called Neural Reflectance Surfaces (NeRS). NeRS learns a neural shape representation of a closed…
Ubisoft China AI & Data Lab（育碧中国AI与数据实验室）；Sichuan University（四川大学）；Ubisoft, Singapore（育碧新加坡）；INRIA Nancy Grand Est（法国国家信息与自动化研究所南锡大东区中心）
This work introduces a novel strategy for generating synthetic training data for 2D and 3D pose estimation of animals using keyframe animations. With the objective to automate the process of creating animations for wildlife, we train several 2D and 3D pose estimation models with synthetic data, and put in place an end-to-end pipeline called ZooBuilder. The pipeline takes as input a video of an animal in the wild, and generates the corresponding 2D and 3D coordinates for each joint of the animal's skeleton. With this approach, we produce motion capture data that can be used to create animations…
Gait recognition has a rapid development in recent years. However, gait recognition in the wild is not well explored yet. An obvious reason could be ascribed to the lack of diverse training data from the perspective of intrinsic and extrinsic factors. To remedy this problem, we propose to construct a large-scale gait dataset with the help of controllable computer simulation. In detail, to diversify the intrinsic factors of gait, we generate numerous characters with diverse attributes and empower them with various types of walking styles. To diversify the extrinsic factors of gait, we build a c…
This paper addresses the problem of monocular 3D human shape and pose estimation from an RGB image. Despite great progress in this field in terms of pose prediction accuracy, state-of-the-art methods often predict inaccurate body shapes. We suggest that this is primarily due to the scarcity of in-the-wild training data with diverse and accurate body shape labels. Thus, we propose STRAPS (Synthetic Training for Real Accurate Pose and Shape), a system that utilises proxy representations, such as silhouettes and 2D joints, as inputs to a shape and pose regression neural network, which is trained …
This paper describes the fourth Affective Behavior Analysis in-the-wild (ABAW) Competition, held in conjunction with European Conference on Computer Vision (ECCV), 2022. The 4th ABAW Competition is a continuation of the Competitions held at IEEE CVPR 2022, ICCV 2021, IEEE FG 2020 and IEEE CVPR 2017 Conferences, and aims at automatically analyzing affect. In the previous runs of this Competition, the Challenges targeted Valence-Arousal Estimation, Expression Classification and Action Unit Detection. This year the Competition encompasses two different Challenges: i) a Multi-Task-Learning one in …
Seoul National University of Science and Technology（首尔科学技术大学）；Kumoh National Institute of Technology（锦湖国立理工学院）
Facial expression in-the-wild is essential for various interactive computing domains. Especially, "Learning from Synthetic Data" (LSD) is an important topic in the facial expression recognition task. In this paper, we propose a multi-task learning-based facial expression recognition approach which consists of emotion and appearance learning branches that can share all face information, and present preliminary results for the LSD challenge introduced in the 4th affective behavior analysis in-the-wild (ABAW) competition. Our method achieved the mean F1 score of 0.71.
The reflections caused by common semi-reflectors, such as glass windows, can impact the performance of computer vision algorithms. State-of-the-art methods can remove reflections on synthetic data and in controlled scenarios. However, they are based on strong assumptions and do not generalize well to real-world images. Contrary to a common misconception, real-world images are challenging even when polarization information is used. We present a deep learning approach to separate the reflected and the transmitted components of the recorded irradiance, which explicitly uses the polarization prope…
University of Science and Technology of China（中国科学技术大学）
Learning from synthetic images plays an important role in facial expression recognition task due to the difficulties of labeling the real images, and it is challenging because of the gap between the synthetic images and real images. The fourth Affective Behavior Analysis in-the-wild Competition raises the challenge and provides the synthetic images generated from Aff-Wild2 dataset. In this paper, we propose a hand-assisted expression recognition method to reduce the gap between the synthetic data and real data. Our method consists of two parts: expression recognition module and hand prediction…
University of Maryland, College Park（马里兰大学帕克分校）；University of California, Berkeley（加州大学伯克利分校）
We present SfSNet, an end-to-end learning framework for producing an accurate decomposition of an unconstrained human face image into shape, reflectance and illuminance. SfSNet is designed to reflect a physical lambertian rendering model. SfSNet learns from a mixture of labeled synthetic and unlabeled real world images. This allows the network to capture low frequency variations from synthetic and high frequency details from real images through the photometric reconstruction loss. SfSNet consists of a new decomposition architecture with residual blocks that learns a complete separation of albe…
Lacking Data? No worries! How synthetic images can alleviate image scarcity in wildlife surveys: a case study with muskox (Ovibos moschatus)
Université de Sherbrooke（舍布鲁克大学）；Ministère de l’Environnement, de la Lutte contre les Changements Climatiques, de la Faune et des Parcs (MELCCFP)（环境、应对气候变化、野生动物与公园部）；Quebec Centre for Biodiversity Science (QCBS)（魁北克生物多样性科学中心）；McGill University（麦吉尔大学）
WILD: a new in-the-Wild Image Linkage Dataset for synthetic image attribution
University of Siena, Department of Information Engineering an Mathematics, Italy（西尔维亚大学信息工程与数学系，意大利）；Politecnico di Milano, Department of Electronics, Informatics, and Bioengineering, Italy（米兰理工学院电子、信息技术与生物工程系，意大利）；University of Trento, Department of Information Engineering and Computer Science, Italy（特伦托大学信息工程与计算机科学系，意大利）；University of Catania, Department of Mathematics and Computer Science, Italy（卡塔尼亚大学数学与计算机科学系，意大利）；Sapienza University of Rome - Departement of Computer, Control and Management Engineering, Italy（罗马萨皮恩扎大学计算机、控制与管理工程系，意大利）
Eurecat, Centre Tecnològic de Catalunya（加泰罗尼亚技术中心Eurecat）
Existing face datasets often lack sufficient representation of occluding objects, which can hinder recognition, but also supply meaningful information to understand the visual context. In this work, we introduce Extended Labeled Faces in-the-Wild (ELFW), a dataset supplementing with additional face-related categories -- and also additional faces -- the originally released semantic labels in the vastly used Labeled Faces in-the-Wild (LFW) dataset. Additionally, two object-based data augmentation techniques are deployed to synthetically enrich under-represented categories which, in benchmarking …
Zhejiang University（浙江大学）；Tencent（腾讯）；University of Hong Kong（香港大学）
Deep learning-based scene text detection can achieve preferable performance, powered with sufficient labeled training data. However, manual labeling is time consuming and laborious. At the extreme, the corresponding annotated data are unavailable. Exploiting synthetic data is a very promising solution except for domain distribution mismatches between synthetic datasets and real datasets. To address the severe domain distribution mismatch, we propose a synthetic-to-real domain adaptation method for scene text detection, which transfers knowledge from synthetic data (source domain) to real data …
Stony Brook University（石溪大学）；Computer Vision Center（计算机视觉中心）；Universitat Autònoma de Barcelona（巴塞罗那自治大学）
Automatic document content processing is affected by artifacts caused by the shape of the paper, non-uniform and diverse color of lighting conditions. Fully-supervised methods on real data are impossible due to the large amount of data needed. Hence, the current state of the art deep learning models are trained on fully or partially synthetic images. However, document shadow or shading removal results still suffer because: (a) prior methods rely on uniformity of local color statistics, which limit their application on real-scenarios with complex document shapes and textures and; (b) synthetic …
Delivering immersive, 3D experiences for human communication requires a method to obtain 360 degree photo-realistic avatars of humans. To make these experiences accessible to all, only commodity hardware, like mobile phone cameras, should be necessary to capture the data needed for avatar creation. For avatars to be rendered realistically from any viewpoint, we require training images and camera poses from all angles. However, we cannot rely on there being trackable features in the foreground or background of all images for use in estimating poses, especially from the side or back of the head.…
Uber ATG；University of Toronto（多伦多大学）；Massachusetts Institute of Technology（麻省理工学院）
Reconstructing high-quality 3D objects from sparse, partial observations from a single view is of crucial importance for various applications in computer vision, robotics, and graphics. While recent neural implicit modeling methods show promising results on synthetic or dense data, they perform poorly on sparse and noisy real-world data. We discover that the limitations of a popular neural implicit model are due to lack of robust shape priors and lack of proper regularization. In this work, we demonstrate highquality in-the-wild shape reconstruction using: (i) a deep encoder as a robust-initia…
Inria Grenoble Rhône-Alpes（法国国家信息与自动化研究所格勒诺布尔-罗纳-阿尔卑斯分校）；Laboratoire Jean Kuntzmann（让·昆茨曼实验室）
This paper addresses the problem of 3D human pose estimation in the wild. A significant challenge is the lack of training data, i.e., 2D images of humans annotated with 3D poses. Such data is necessary to train state-of-the-art CNN architectures. Here, we propose a solution to generate a large set of photorealistic synthetic images of humans with 3D pose annotations. We introduce an image-based synthesis engine that artificially augments a dataset of real images with 2D human pose annotations using 3D Motion Capture (MoCap) data. Given a candidate 3D pose our algorithm selects for each joint a…
The University of Hong Kong（香港大学）；SenseTime Research（商汤科技研究院）；Nanjing University（南京大学）；The University of Adelaide（阿德莱德大学）；Huazhong University of Science and Technology（华中科技大学）
Low-resolution text images are often seen in natural scenes such as documents captured by mobile phones. Recognizing low-resolution text images is challenging because they lose detailed content information, leading to poor recognition accuracy. An intuitive solution is to introduce super-resolution (SR) techniques as pre-processing. However, previous single image super-resolution (SISR) methods are trained on synthetic low-resolution images (e.g.Bicubic down-sampling), which is simple and not suitable for real low-resolution text recognition. To this end, we pro-pose a real scene text SR datas…
In this paper, we present the results of the HSE-NN team in the 4th competition on Affective Behavior Analysis in-the-wild (ABAW). The novel multi-task EfficientNet model is trained for simultaneous recognition of facial expressions and prediction of valence and arousal on static photos. The resulting MT-EmotiEffNet extracts visual features that are fed into simple feed-forward neural networks in the multi-task learning challenge. We obtain performance measure 1.3 on the validation set, which is significantly greater when compared to either performance of baseline (0.3) or existing models that…
Meta Reality Labs Research（Meta现实实验室）；Seoul National University（首尔国立大学）
Although much progress has been made in 3D clothed human reconstruction, most of the existing methods fail to produce robust results from in-the-wild images, which contain diverse human poses and appearances. This is mainly due to the large domain gap between training datasets and in-the-wild datasets. The training datasets are usually synthetic ones, which contain rendered images from GT 3D scans. However, such datasets contain simple human poses and less natural image appearances compared to those of real in-the-wild datasets, which makes generalization of it to in-the-wild images extremely …
The task of image deblurring is a very ill-posed problem as both the image and the blur are unknown. Moreover, when pictures are taken in the wild, this task becomes even more challenging due to the blur varying spatially and the occlusions between the object. Due to the complexity of the general image model we propose a novel convolutional network architecture which directly generates the sharp image.This network is built in three stages, and exploits the benefits of pyramid schemes often used in blind deconvolution. One of the main difficulties in training such a network is to design a suita…
Center for Machine Vision Research and Signal Analysis（机器视觉研究与信号分析中心）；University of Oulu（奥卢大学）
We present a method to reconstruct a dense spatio-temporal depth map of a non-rigidly deformable object directly from a video sequence. The estimation of depth is performed locally on spatio-temporal patches of the video, and then the full depth video of the entire shape is recovered by combining them together. Since the geometric complexity of a local spatio-temporal patch of a deforming non-rigid object is often simple enough to be faithfully represented with a parametric model, we artificially generate a database of small deforming rectangular meshes rendered with different material propert…
Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）
Convolutional Neural Network based approaches for monocular 3D human pose estimation usually require a large amount of training images with 3D pose annotations. While it is feasible to provide 2D joint annotations for large corpora of in-the-wild images with humans, providing accurate 3D annotations to such in-the-wild corpora is hardly feasible in practice. Most existing 3D labelled data sets are either synthetically created or feature in-studio images. 3D pose estimation algorithms trained on such data often have limited ability to generalize to real world scene diversity. We therefore propo…
Carnegie Mellon University（卡内基梅隆大学）；Facebook AI Research（脸书人工智能研究院）
We aim to infer 3D shape and pose of object from a single image and propose a learning-based approach that can train from unstructured image collections, supervised by only segmentation outputs from off-the-shelf recognition systems (i.e. 'shelf-supervised'). We first infer a volumetric representation in a canonical frame, along with the camera pose. We enforce the representation geometrically consistent with both appearance and masks, and also that the synthesized novel views are indistinguishable from image collections. The coarse volumetric prediction is then converted to a mesh-based repre…
The ability to perceive 3D human bodies from a single image has a multitude of applications ranging from entertainment and robotics to neuroscience and healthcare. A fundamental challenge in human mesh recovery is in collecting the ground truth 3D mesh targets required for training, which requires burdensome motion capturing systems and is often limited to indoor laboratories. As a result, while progress is made on benchmark datasets collected in these restrictive settings, models fail to generalize to real-world "in-the-wild" scenarios due to distribution shifts. We propose Domain Adaptive 3D…
Egocentric 3D human pose estimation with a single fisheye camera has drawn a significant amount of attention recently. However, existing methods struggle with pose estimation from in-the-wild images, because they can only be trained on synthetic data due to the unavailability of large-scale in-the-wild egocentric datasets. Furthermore, these methods easily fail when the body parts are occluded by or interacting with the surrounding scene. To address the shortage of in-the-wild data, we collect a large-scale in-the-wild egocentric dataset called Egocentric Poses in the Wild (EgoPW). This datase…
Synthetic visual data can provide practically infinite diversity and rich labels, while avoiding ethical issues with privacy and bias. However, for many tasks, current models trained on synthetic data generalize poorly to real data. The task of 3D human pose estimation is a particularly interesting example of this sim2real problem, because learning-based approaches perform reasonably well given real training data, yet labeled 3D poses are extremely difficult to obtain in the wild, limiting scalability. In this paper, we show that standard neural-network approaches, which perform poorly when tr…
We propose an end-to-end pipeline for both building and tracking 3D facial models from personalized in-the-wild (cellphone, webcam, youtube clips, etc.) video data. First, we present a method for automatic data curation and retrieval based on a hierarchical clustering framework typical of collision detection algorithms in traditional computer graphics pipelines. Subsequently, we utilize synthetic turntables and leverage deepfake technology in order to build a synthetic multi-view stereo pipeline for appearance capture that is robust to imperfect synthetic geometry and image misalignment. The r…
Huazhong University of Science and Technology（华中科技大学）；Ant Group（蚂蚁集团）
Facial affect analysis remains a challenging task with its setting transitioned from lab-controlled to in-the-wild situations. In this paper, we present novel frameworks to handle the two challenges in the 4th Affective Behavior Analysis In-The-Wild (ABAW) competition: i) Multi-Task-Learning (MTL) Challenge and ii) Learning from Synthetic Data (LSD) Challenge. For MTL challenge, we adopt the SMM-EmotionNet with a better ensemble strategy of feature vectors. For LSD challenge, we propose respective methods to combat the problems of single labels, imbalanced distribution, fine-tuning limitations…
This paper performs comprehensive analysis on datasets for occlusion-aware face segmentation, a task that is crucial for many downstream applications. The collection and annotation of such datasets are time-consuming and labor-intensive. Although some efforts have been made in synthetic data generation, the naturalistic aspect of data remains less explored. In our study, we propose two occlusion generation techniques, Naturalistic Occlusion Generation (NatOcc), for producing high-quality naturalistic synthetic occluded faces; and Random Occlusion Generation (RandOcc), a more general synthetic …
Institute of Computer Graphics and Vision, Graz University of Technology, Austria（奥地利格拉茨工业大学计算机图形与视觉研究所）
We present Location Field Descriptors, a novel approach for single image 3D model retrieval in the wild. In contrast to previous methods that directly map 3D models and RGB images to an embedding space, we establish a common low-level representation in the form of location fields from which we compute pose invariant 3D shape descriptors. Location fields encode correspondences between 2D pixels and 3D surface coordinates and, thus, explicitly capture 3D shape and 3D pose information without appearance variations which are irrelevant for the task. This early fusion of 3D models and RGB images re…
