We present a self-supervised human mesh recovery framework to infer human pose and shape from monocular images in the absence of any paired supervision. Recent advances have shifted the interest towards directly regressing parameters of a parametric human model by supervising them on large-scale datasets with 2D landmark annotations. This limits the generalizability of such approaches to operate on images from unlabeled wild environments. Acknowledging this we propose a novel appearance consensus driven self-supervised objective. To effectively disentangle the foreground (FG) human we rely on image pairs depicting the same person (consistent FG) in varied pose and background (BG) which are obtained from unlabeled wild videos. The proposed FG appearance consistency objective makes use of a novel, differentiable Color-recovery module to obtain vertex colors without the need for any appearance network; via efficient realization of color-picking and reflectional symmetry. We achieve state-of-the-art results on the standard model-based 3D pose estimation benchmarks at comparable supervision levels. Furthermore, the resulting colored mesh prediction opens up the usage of our framework for a variety of appearance-related tasks beyond the pose and shape estimation, thus establishing our superior generalizability.
MGAvatar: Mesh-Bound Gaussians for Head Avatar Geometry and Appearance Modeling
Beijing Normal-Hong Kong Baptist University（北京师范大学-香港浸会大学联合国际学院）；Xiamen University（厦门大学）；The University of Texas at Dallas（德克萨斯大学达拉斯分校）；Jimei University（集美大学）
Direct and Adaptable Mesh-Gaussian Scene Reconstruction from Multi-View Images
School of Computer Science, Australian Artificial Intelligence Institute (AAII)（计算机科学学院，澳大利亚人工智能研究所）；University of Technology Sydney（悉尼技术大学）；School of Automobile（汽车学院）；Chang’an University（长安大学）
Warsaw University of Technology（华沙理工大学）；Google（谷歌）
In this paper, we present a framework for computing dense keypoint correspondences between images under strong scene appearance changes. Traditional methods, based on nearest neighbour search in the feature descriptor space, perform poorly when environmental conditions vary, e.g. when images are taken at different times of the day or seasons. Our method improves finding keypoint correspondences in such difficult conditions. First, we use Neighbourhood Consensus Networks to build spatially consistent matching grid between two images at a coarse scale. Then, we apply Superpoint-like corner detec…
Person re-identification aims to associate images of the same person over multiple non-overlapping camera views at different times. Depending on the human operator, manual re-identification in large camera networks is highly time consuming and erroneous. Automated person re-identification is required due to the extensive quantity of visual data produced by rapid inflation of large scale distributed multi-camera systems. The state-of-the-art works focus on learning and factorize person appearance features into latent discriminative factors at multiple semantic levels. We propose Deep Parallel F…
Institute of Industrial Science, The University of Tokyo（东京大学生产技术研究所）；OMRON SINIC X Corporation（欧姆龙SINIC X公司）
Hand segmentation is a crucial task in first-person vision. Since first-person images exhibit strong bias in appearance among different environments, adapting a pre-trained segmentation model to a new domain is required in hand segmentation. Here, we focus on appearance gaps for hand regions and backgrounds separately. We propose (i) foreground-aware image stylization and (ii) consensus pseudo-labeling for domain adaptation of hand segmentation. We stylize source images independently for the foreground and background using target images as style. To resolve the domain shift that the stylizatio…
Most of the recent deep learning-based 3D human pose and mesh estimation methods regress the pose and shape parameters of human mesh models, such as SMPL and MANO, from an input image. The first weakness of these methods is an appearance domain gap problem, due to different image appearance between train data from controlled environments, such as a laboratory, and test data from in-the-wild environments. The second weakness is that the estimation of the pose parameters is quite challenging owing to the representation issues of 3D rotations. To overcome the above weaknesses, we propose Pose2Mes…
We present a novel approach for tracking multiple people in video. Unlike past approaches which employ 2D representations, we focus on using 3D representations of people, located in three-dimensional space. To this end, we develop a method, Human Mesh and Appearance Recovery (HMAR) which in addition to extracting the 3D geometry of the person as a SMPL mesh, also extracts appearance as a texture map on the triangles of the mesh. This serves as a 3D representation for appearance that is robust to viewpoint and pose changes. Given a video clip, we first detect bounding boxes corresponding to peo…
SplattingAvatar: Realistic Real-Time Human Avatars with Mesh-Embedded Gaussian Splatting
The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；Prometheus Vision Technology Co., Ltd.（天演智视科技有限公司）；The Hong Kong University of Science and Technology（香港科技大学）
EPFL（洛桑联邦理工学院）；UBC（不列颠哥伦比亚大学）；Balgrist University Hospital（巴尔格里斯特大学医院）；ClearSpace SA（ClearSpace公司）
Self-supervised detection and segmentation of foreground objects aims for accuracy without annotated training data. However, existing approaches predominantly rely on restrictive assumptions on appearance and motion. For scenes with dynamic activities and camera motion, we propose a multi-camera framework in which geometric constraints are embedded in the form of multi-view consistency during training via coarse 3D localization in a voxel grid and fine-grained offset regression. In this manner, we learn a joint distribution of proposals over multiple views. At inference time, our method operat…
Object-IR: Leveraging Object Consistency and Mesh Deformation for Self-Supervised Image Retargeting
Key Laboratory of Grain Information Processing and Control（粮食信息处理与控制重点实验室）；College of Information Science and Engineering（信息科学与工程学院）；Institute for Complexity Science（复杂科学研究所）
SuperCarver: Texture-Consistent 3D Geometry Super-Resolution for High-Fidelity Surface Detail Generation
Tencent Games, China（腾讯游戏，中国）；Department of Computer Science & Engineering, Texas A & M University（电子与计算机工程系，德克萨斯A&M大学）；Department of Computer Science, City University of Hong Kong（计算机科学系，香港城市大学）
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…
Image stitching for two images without a global transformation between them is notoriously difficult. In this paper, noticing the importance of planar structure under perspective geometry, we propose a new image stitching method which stitches images by allowing for the alignment of a set of matched dominant planar regions. Clearly different from previous methods resorting to plane segmentation, the key to our approach is to utilize rich semantic information directly from RGB images to extract planar image regions with a deep Convolutional Neural Network (CNN). We specifically design a new mod…
Sun Yat-sen University（中山大学）；Peng Cheng Laboratory（鹏城实验室）；Tencent PCG（腾讯平台与内容事业群）；HKUST（香港科技大学）；Pazhou Lab（琶洲实验室）
Weakly supervised temporal action localization (WS-TAL) is a challenging task that aims to localize action instances in the given video with video-level categorical supervision. Both appearance and motion features are used in previous works, while they do not utilize them in a proper way but apply simple concatenation or score-level fusion. In this work, we argue that the features extracted from the pretrained extractor, e.g., I3D, are not the WS-TALtask-specific features, thus the feature re-calibration is needed for reducing the task-irrelevant information redundancy. Therefore, we propose a…
Fancy123: One Image to High-Quality 3D Mesh Generation via Plug-and-Play Deformation
Huazhong University of Science and Technology（华中科技大学）；Guangdong Intelligent Robotics Institute（广东智能机器人研究院）；South China University of Technology（华南理工大学）；Pazhou Laboratory（琶洲实验室）
We present a learning framework for recovering the 3D shape, camera, and texture of an object from a single image. The shape is represented as a deformable 3D mesh model of an object category where a shape is parameterized by a learned mean shape and per-instance predicted deformation. Our approach allows leveraging an annotated image collection for training, where the deformable model and the 3D prediction mechanism are learned without relying on ground-truth 3D or multi-view supervision. Our representation enables us to go beyond existing 3D prediction approaches by incorporating texture inf…
Santa Creu i Sant Pau Hospital（圣十字圣保罗医院）；Universitat Autonòma Barcelona（巴塞罗那自治大学）；Vrije University Medical Centre Amsterdam（阿姆斯特丹自由大学医学中心）
Classification and differentiation of small pathological objects may greatly vary among human raters due to differences in training, expertise and their consistency over time. In a radiological setting, objects commonly have high within-class appearance variability whilst sharing certain characteristics across different classes, making their distinction even more difficult. As an example, markers of cerebral small vessel disease, such as enlarged perivascular spaces (EPVS) and lacunes, can be very varied in their appearance while exhibiting high inter-class similarity, making this task highly …
In the era of autonomous driving, urban mapping represents a core step to let vehicles interact with the urban context. Successful mapping algorithms have been proposed in the last decade building the map leveraging on data from a single sensor. The focus of the system presented in this paper is twofold: the joint estimation of a 3D map from lidar data and images, based on a 3D mesh, and its texturing. Indeed, even if most surveying vehicles for mapping are endowed by cameras and lidar, existing mapping algorithms usually rely on either images or lidar data; moreover both image-based and lidar…
Institute of Industrial Science, The University of Tokyo（东京大学工业科学研究所）
Despite recent advances in appearance-based gaze estimation techniques, the need for training data that covers the target head pose and gaze distribution remains a crucial challenge for practical deployment. This work examines a novel approach for synthesizing gaze estimation training data based on monocular 3D face reconstruction. Unlike prior works using multi-view reconstruction, photo-realistic CG models, or generative neural networks, our approach can manipulate and extend the head pose range of existing training data without any additional requirements. We introduce a projective matching…
South China University of Technology（华南理工大学）；DexForce Co. Ltd.（德擎科技有限公司）；The Hong Kong Polytechnic University（香港理工大学）；Peng Cheng Laboratory（鹏城实验室）
Creation of 3D content by stylization is a promising yet challenging problem in computer vision and graphics research. In this work, we focus on stylizing photorealistic appearance renderings of a given surface mesh of arbitrary topology. Motivated by the recent surge of cross-modal supervision of the Contrastive Language-Image Pre-training (CLIP) model, we propose TANGO, which transfers the appearance style of a given 3D shape according to a text prompt in a photorealistic manner. Technically, we propose to disentangle the appearance style as the spatially varying bidirectional reflectance di…
Queen Mary University of London（伦敦玛丽女王大学）；Fondazione Bruno Kessler（布鲁诺·凯斯勒基金会）
Novel-View Human Action Synthesis aims to synthesize the movement of a body from a virtual viewpoint, given a video from a real viewpoint. We present a novel 3D reasoning to synthesize the target viewpoint. We first estimate the 3D mesh of the target body and transfer the rough textures from the 2D images to the mesh. As this transfer may generate sparse textures on the mesh due to frame resolution or occlusions. We produce a semi-dense textured mesh by propagating the transferred textures both locally, within local geodesic neighborhoods, and globally, across symmetric semantic parts. Next, w…
Neural Surface Priors for Editable Gaussian Splatting
IDEAS NCBR；Adam Mickiewicz University（亚当·密茨凯维奇大学）；Wrocław University of Science and Technology（弗罗茨瓦夫理工大学）；Jagiellonian University（雅盖隆大学）；Tooploox；New Jersey Institute of Technology（新泽西理工学院）
RMAvatar: Photorealistic Human Avatar Reconstruction from Monocular Video Based on Rectified Mesh-embedded Gaussians
College of Computer Engineering, Jimei University（集美大学计算机工程学院）；National Institute for Data Science in Health and Medicine, Xiamen University（厦门大学健康与医学数据科学国家研究院）；The University of Texas at Dallas（德克萨斯大学达拉斯分校）；School of Informatics, Xiamen University（厦门大学信息学院）；BNU-HKBU United International College（北京师范大学-香港浸会大学联合国际学院）
Seoul National University（首尔大学）；Hanyang University（汉阳大学）；Gachon University（嘉泉大学）
In this paper, we address the problem of estimating a 3D human pose from a single image, which is important but difficult to solve due to many reasons, such as self-occlusions, wild appearance changes, and inherent ambiguities of 3D estimation from a 2D cue. These difficulties make the problem ill-posed, which have become requiring increasingly complex estimators to enhance the performance. On the other hand, most existing methods try to handle this problem based on a single complex estimator, which might not be good solutions. In this paper, to resolve this issue, we propose a multiple-partia…
Inria（法国国家信息与自动化研究所）；Czech Technical University in Prague（布拉格捷克理工大学）；DeepMind（深度思考）；Tokyo Institute of Technology（东京工业大学）
We address the problem of finding reliable dense correspondences between a pair of images. This is a challenging task due to strong appearance differences between the corresponding scene elements and ambiguities generated by repetitive patterns. The contributions of this work are threefold. First, inspired by the classic idea of disambiguating feature matches using semi-local constraints, we develop an end-to-end trainable convolutional neural network architecture that identifies sets of spatially consistent matches by analyzing neighbourhood consensus patterns in the 4D space of all possible …
Zhejiang University（浙江大学）；University of Technology Sydney（悉尼科技大学）；National University of Singapore（新加坡国立大学）；Université de Montréal（蒙特利尔大学）；Huawei Cloud（华为云）
Understanding human emotions is a crucial ability for intelligent robots to provide better human-robot interactions. The existing works are limited to trimmed video-level emotion classification, failing to locate the temporal window corresponding to the emotion. In this paper, we introduce a new task, named Temporal Emotion Localization in videos~(TEL), which aims to detect human emotions and localize their corresponding temporal boundaries in untrimmed videos with aligned subtitles. TEL presents three unique challenges compared to temporal action localization: 1) The emotions have extremely v…
Videos from edited media like movies are a useful, yet under-explored source of information. The rich variety of appearance and interactions between humans depicted over a large temporal context in these films could be a valuable source of data. However, the richness of data comes at the expense of fundamental challenges such as abrupt shot changes and close up shots of actors with heavy truncation, which limits the applicability of existing human 3D understanding methods. In this paper, we address these limitations with an insight that while shot changes of the same scene incur a discontinuit…
