Though much progress has been achieved in single-image 3D human recovery, estimating 3D model for in-the-wild images remains a formidable challenge. The reason lies in the fact that obtaining high-quality 3D annotations for in-the-wild images is an extremely hard task that consumes enormous amount of resources and manpower. To tackle this problem, previous methods adopt a hybrid training strategy that exploits multiple heterogeneous types of annotations including 3D and 2D while leaving the efficacy of each annotation not thoroughly investigated. In this work, we aim to perform a comprehensive study on cost and effectiveness trade-off between different annotations. Specifically, we focus on the challenging task of in-the-wild 3D human recovery from single images when paired 3D annotations are not fully available. Through extensive experiments, we obtain several observations: 1) 3D annotations are efficient, whereas traditional 2D annotations such as 2D keypoints and body part segmentation are less competent in guiding 3D human recovery. 2) Dense Correspondence such as DensePose is effective. When there are no paired in-the-wild 3D annotations available, the model exploiting dense correspondence can achieve 92% of the performance compared to a model trained with paired 3D data. We show that incorporating dense correspondence into in-the-wild 3D human recovery is promising and competitive due to its high efficiency and relatively low annotating cost. Our model trained with dense correspondence can serve as a strong reference for future research.
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…
Indian Institute of Science, Bangalore（印度科学理工学院）；Google Research（谷歌研究院）
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 …
SAM-Body4D: Training-Free 4D Human Body Mesh Recovery from Videos
Department of Automation, Tsinghua University, Beijing, China（自动化系，清华大学，北京，中国）；University of Warwick, Coventry, UK（沃里克大学，英国）；University of Sheffield, Sheffield, UK（谢菲尔德大学，英国）
University of California, Berkeley（加州大学伯克利分校）；MPI for Intelligent Systems（马克斯·普朗克智能系统研究所）；University of Maryland, College Park（马里兰大学帕克分校）
We describe Human Mesh Recovery (HMR), an end-to-end framework for reconstructing a full 3D mesh of a human body from a single RGB image. In contrast to most current methods that compute 2D or 3D joint locations, we produce a richer and more useful mesh representation that is parameterized by shape and 3D joint angles. The main objective is to minimize the reprojection loss of keypoints, which allow our model to be trained using images in-the-wild that only have ground truth 2D annotations. However, the reprojection loss alone leaves the model highly under constrained. In this work we address …
Carnegie Mellon University（卡内基梅隆大学）；Argo AI, LLC（Argo AI 有限责任公司）
The recovery of 3D shape and pose from 2D landmarks stemming from a large ensemble of images can be viewed as a non-rigid structure from motion (NRSfM) problem. Classical NRSfM approaches, however, are problematic as they rely on heuristic priors on the 3D structure (e.g. low rank) that do not scale well to large datasets. Learning-based methods are showing the potential to reconstruct a much broader set of 3D structures than classical methods -- dramatically expanding the importance of NRSfM to atemporal unsupervised 2D to 3D lifting. Hitherto, these learning approaches have not been able to …
Diffusion Models are Efficient Data Generators for Human Mesh Recovery
The University of Adelaide（阿德莱德大学）；Zhejiang University（浙江大学）；Zhejiang University of Technology（浙江工业大学）；The University of Hong Kong（香港大学）；SenseTime（秒针科技）
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）
Face images in the wild undergo large intra-personal variations, such as poses, illuminations, occlusions, and low resolutions, which cause great challenges to face-related applications. This paper addresses this challenge by proposing a new deep learning framework that can recover the canonical view of face images. It dramatically reduces the intra-person variances, while maintaining the inter-person discriminativeness. Unlike the existing face reconstruction methods that were either evaluated in controlled 2D environment or employed 3D information, our approach directly learns the transforma…
Towards Metric-Aware Multi-Person Mesh Recovery by Jointly Optimizing Human Crowd in Camera Space
Department of Electronic Engineering, Tsinghua University（清华大学电子工程系）；College of AI, Tsinghua University（清华大学人工智能学院）；Beijing National Research Center for Information Science and Technology（北京信息科学与技术国家研究中心）
Stony Brook University（石溪大学）；Institut de Robòtica i Informàtica Industrial, CSIC-UPC（机器人学与信息学研究所（西班牙国家研究委员会-加泰罗尼亚理工大学联合机构））
We present SIDER(Single-Image neural optimization for facial geometric DEtail Recovery), a novel photometric optimization method that recovers detailed facial geometry from a single image in an unsupervised manner. Inspired by classical techniques of coarse-to-fine optimization and recent advances in implicit neural representations of 3D shape, SIDER combines a geometry prior based on statistical models and Signed Distance Functions (SDFs) to recover facial details from single images. First, it estimates a coarse geometry using a morphable model represented as an SDF. Next, it reconstructs fac…
Harbin Institute of Technology（哈尔滨工业大学）；JD AI Research（京东人工智能研究院）
We describe an end-to-end method for recovering 3D human body mesh from single images and monocular videos. Different from the existing methods try to obtain all the complex 3D pose, shape, and camera parameters from one coupling feature, we propose a skeleton-disentangling based framework, which divides this task into multi-level spatial and temporal granularity in a decoupling manner. In spatial, we propose an effective and pluggable "disentangling the skeleton from the details" (DSD) module. It reduces the complexity and decouples the skeleton, which lays a good foundation for temporal mode…
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…
Shanghai Jiao Tong University（上海交通大学）；Imperial College London（帝国理工学院）；Huawei CBG（华为消费者业务集团）
Learning a dense 3D model with fine-scale details from a single facial image is highly challenging and ill-posed. To address this problem, many approaches fit smooth geometries through facial prior while learning details as additional displacement maps or personalized basis. However, these techniques typically require vast datasets of paired multi-view data or 3D scans, whereas such datasets are scarce and expensive. To alleviate heavy data dependency, we present a robust texture-guided geometric detail recovery approach using only a single in-the-wild facial image. More specifically, our meth…
Computer Vision Center（计算机视觉中心）；Universitat de Barcelona（巴塞罗那大学）
Current state-of-the-art in 3D human pose and shape recovery relies on deep neural networks and statistical morphable body models, such as the Skinned Multi-Person Linear model (SMPL). However, regardless of the advantages of having both body pose and shape, SMPL-based solutions have shown difficulties to predict 3D bodies accurately. This is mainly due to the unconstrained nature of SMPL, which may generate unrealistic body meshes. Because of this, regression of SMPL parameters is a difficult task, often addressed with complex regularization terms. In this paper we propose to embed SMPL withi…
Meta Reality Labs Research（Meta现实实验室）；Seoul National University（首尔国立大学）
Hands, one of the most dynamic parts of our body, suffer from blur due to their active movements. However, previous 3D hand mesh recovery methods have mainly focused on sharp hand images rather than considering blur due to the absence of datasets providing blurry hand images. We first present a novel dataset BlurHand, which contains blurry hand images with 3D groundtruths. The BlurHand is constructed by synthesizing motion blur from sequential sharp hand images, imitating realistic and natural motion blurs. In addition to the new dataset, we propose BlurHandNet, a baseline network for accurate…
Mocap-2-to-3: Multi-view Lifting for Monocular Motion Recovery with 2D Pretraining
Beijing Institute of Technology（北京理工大学）；State Key Laboratory of General Artificial Intelligence, BIGAI（国家一般人工智能重点实验室，BIGAI）；Deep Glint；Zhejiang University（浙江大学）；The University of Hong Kong（香港大学）；Shandong Agricultural University（山东农业大学）
Recovering 3D human mesh from monocular images is a popular topic in computer vision and has a wide range of applications. This paper aims to estimate 3D mesh of multiple body parts (e.g., body, hands) with large-scale differences from a single RGB image. Existing methods are mostly based on iterative optimization, which is very time-consuming. We propose to train a single-shot model to achieve this goal. The main challenge is lacking training data that have complete 3D annotations of all body parts in 2D images. To solve this problem, we design a multi-branch framework to disentangle the regr…
United Imaging Intelligence（联影智能）；University at Buffalo（纽约州立大学布法罗分校）
To date, little attention has been given to multi-view 3D human mesh estimation, despite real-life applicability (e.g., motion capture, sport analysis) and robustness to single-view ambiguities. Existing solutions typically suffer from poor generalization performance to new settings, largely due to the limited diversity of image-mesh pairs in multi-view training data. To address this shortcoming, people have explored the use of synthetic images. But besides the usual impact of visual gap between rendered and target data, synthetic-data-driven multi-view estimators also suffer from overfitting …
DICE: End-to-end Deformation Capture of Hand-Face Interactions from a Single Image
University of Pennsylvania（宾夕法尼亚大学）；The University of Hong Kong（香港大学）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；University of Cambridge（剑桥大学）；Texas A&M University（德克萨斯农工大学）；TransGP
We present an approach for 3D global human mesh recovery from monocular videos recorded with dynamic cameras. Our approach is robust to severe and long-term occlusions and tracks human bodies even when they go outside the camera's field of view. To achieve this, we first propose a deep generative motion infiller, which autoregressively infills the body motions of occluded humans based on visible motions. Additionally, in contrast to prior work, our approach reconstructs human meshes in consistent global coordinates even with dynamic cameras. Since the joint reconstruction of human motions and …
Indian Institute of Science（印度科学学院）；Google Research（谷歌研究院）
Articulation-centric 2D/3D pose supervision forms the core training objective in most existing 3D human pose estimation techniques. Except for synthetic source environments, acquiring such rich supervision for each real target domain at deployment is highly inconvenient. However, we realize that standard foreground silhouette estimation techniques (on static camera feeds) remain unaffected by domain-shifts. Motivated by this, we propose a novel target adaptation framework that relies only on silhouette supervision to adapt a source-trained model-based regressor. However, in the absence of any …
United Imaging Intelligence（联影智能）；University of California Riverside（加州大学河滨分校）
We consider the problem of estimating frame-level full human body meshes given a video of a person with natural motion dynamics. While much progress in this field has been in single image-based mesh estimation, there has been a recent uptick in efforts to infer mesh dynamics from video given its role in alleviating issues such as depth ambiguity and occlusions. However, a key limitation of existing work is the assumption that all the observed motion dynamics can be modeled using one dynamical/recurrent model. While this may work well in cases with relatively simplistic dynamics, inference with…
SmartMore Co., Ltd.（思谋科技有限公司）；Shenzhen Institute of Big Data, The Chinese University of Hong Kong (Shenzhen)（香港中文大学（深圳）深圳大数据研究院）；South China University of Technology（华南理工大学）
Estimating 3D human pose from a single image is a challenging task. This work attempts to address the uncertainty of lifting the detected 2D joints to the 3D space by introducing an intermediate state-Part-Centric Heatmap Triplets (HEMlets), which shortens the gap between the 2D observation and the 3D interpretation. The HEMlets utilize three joint-heatmaps to represent the relative depth information of the end-joints for each skeletal body part. In our approach, a Convolutional Network (ConvNet) is first trained to predict HEMlets from the input image, followed by a volumetric joint-heatmap r…
From an image of a person in action, we can easily guess the 3D motion of the person in the immediate past and future. This is because we have a mental model of 3D human dynamics that we have acquired from observing visual sequences of humans in motion. We present a framework that can similarly learn a representation of 3D dynamics of humans from video via a simple but effective temporal encoding of image features. At test time, from video, the learned temporal representation give rise to smooth 3D mesh predictions. From a single image, our model can recover the current 3D mesh as well as its …
