3D Human Shape and Pose from a Single Low-Resolution Image with Self-Supervised Learning
Robotics Institute, Carnegie Mellon University（卡内基梅隆大学机器人研究所）；Electrical and Computer Engineering, Carnegie Mellon University（卡内基梅隆大学电气与计算机工程系）；Institut de Robòtica i Informàtica Industrial (CSIC-UPC)（工业机器人与信息学研究所（CSIC-UPC））；Facebook Reality Labs (Oculus)（Facebook现实实验室（Oculus））
Xiangyu Xu, Hao Chen, Francesc Moreno-Noguer, Laszlo A. Jeni, Fernando De la Torre
3D human shape and pose estimation from monocular images has been an active area of research in computer vision, having a substantial impact on the development of new applications, from activity recognition to creating virtual avatars. Existing deep learning methods for 3D human shape and pose estimation rely on relatively high-resolution input images; however, high-resolution visual content is not always available in several practical scenarios such as video surveillance and sports broadcasting. Low-resolution images in real scenarios can vary in a wide range of sizes, and a model trained in one resolution does not typically degrade gracefully across resolutions. Two common approaches to solve the problem of low-resolution input are applying super-resolution techniques to the input images which may result in visual artifacts, or simply training one model for each resolution, which is impractical in many realistic applications. To address the above issues, this paper proposes a novel algorithm called RSC-Net, which consists of a Resolution-aware network, a Self-supervision loss, and a Contrastive learning scheme. The proposed network is able to learn the 3D body shape and pose across different resolutions with a single model. The self-supervision loss encourages scale-consistency of the output, and the contrastive learning scheme enforces scale-consistency of the deep features. We show that both these new training losses provide robustness when learning 3D shape and pose in a weakly-supervised manner. Extensive experiments demonstrate that the RSC-Net can achieve consistently better results than the state-of-the-art methods for challenging low-resolution images.
Tarbiat Modares University（塔比亚特·莫达雷斯大学）；ICT Research Institute（信息与通信技术研究院）；Iranian Research Organization for Science and Technology (IROST)（伊朗科学技术研究组织（IROST））
The cost of head pose labeling is the main challenge of improving the fine-grained Head Pose Estimation (HPE). Although Self-Supervised Learning (SSL) can be a solution to the lack of huge amounts of labeled data, its efficacy for fine-grained HPE is not yet fully explored. This study aims to assess the usage of SSL in fine-grained HPE based on two scenarios: (1) using SSL for weights pre-training procedure, and (2) leveraging auxiliary SSL losses besides HPE. We design a Hybrid Multi-Task Learning (HMTL) architecture based on the ResNet50 backbone in which both strategies are applied. Our exp…
Key Laboratory of Machine Perception (MOE), School of EECS, Peking University（北京大学信息科学技术学院机器感知与智能教育部重点实验室）；PKU-SenseTime Machine Vision Joint Lab（北京大学-商汤科技机器视觉联合实验室）
We propose a self-supervised learning framework for visual odometry (VO) that incorporates correlation of consecutive frames and takes advantage of adversarial learning. Previous methods tackle self-supervised VO as a local structure from motion (SfM) problem that recovers depth from single image and relative poses from image pairs by minimizing photometric loss between warped and captured images. As single-view depth estimation is an ill-posed problem, and photometric loss is incapable of discriminating distortion artifacts of warped images, the estimated depth is vague and pose is inaccurate…
University of Linköping（林雪平大学）；University of Waterloo（滑铁卢大学）
This paper describes recent developments in object specific pose and shape prediction from single images. The main contribution is a new approach to camera pose prediction by self-supervised learning of keypoints corresponding to locations on a category specific deformable shape. We designed a network to generate a proxy ground-truth heatmap from a set of keypoints distributed all over the category-specific mean shape, where each is represented by a unique color on a labeled texture. The proxy ground-truth heatmap is used to train a deep keypoint prediction network, which can be used in online…
One major challenge for monocular 3D human pose estimation in-the-wild is the acquisition of training data that contains unconstrained images annotated with accurate 3D poses. In this paper, we address this challenge by proposing a weakly-supervised approach that does not require 3D annotations and learns to estimate 3D poses from unlabeled multi-view data, which can be acquired easily in in-the-wild environments. We propose a novel end-to-end learning framework that enables weakly-supervised training using multi-view consistency. Since multi-view consistency is prone to degenerated solutions,…
Toyota Technological Institute（丰田工业大学）；Nara Institute of Science and Technology（奈良先端科学技术大学院大学）
For human pose estimation in still images, this paper proposes three semi- and weakly-supervised learning schemes. While recent advances of convolutional neural networks improve human pose estimation using supervised training data, our focus is to explore the semi- and weakly-supervised schemes. Our proposed schemes initially learn conventional model(s) for pose estimation from a small amount of standard training images with human pose annotations. For the first semi-supervised learning scheme, this conventional pose model detects candidate poses in training images with no human annotation. Fr…
Multi-animal pose estimation is essential for studying animals' social behaviors in neuroscience and neuroethology. Advanced approaches have been proposed to support multi-animal estimation and achieve state-of-the-art performance. However, these models rarely exploit unlabeled data during training even though real world applications have exponentially more unlabeled frames than labeled frames. Manually adding dense annotations for a large number of images or videos is costly and labor-intensive, especially for multiple instances. Given these deficiencies, we propose a novel semi-supervised ar…
Heidelberg Collaboratory for Image Processing（海德堡图像处理合作实验室）；IWR, Heidelberg University（海德堡大学跨学科科学计算中心）
Human pose analysis is presently dominated by deep convolutional networks trained with extensive manual annotations of joint locations and beyond. To avoid the need for expensive labeling, we exploit spatiotemporal relations in training videos for self-supervised learning of pose embeddings. The key idea is to combine temporal ordering and spatial placement estimation as auxiliary tasks for learning pose similarities in a Siamese convolutional network. Since the self-supervised sampling of both tasks from natural videos can result in ambiguous and incorrect training labels, our method employs …
We present a self-supervised learning algorithm for 3D human pose estimation of a single person based on a multiple-view camera system and 2D body pose estimates for each view. To train our model, represented by a deep neural network, we propose a four-loss function learning algorithm, which does not require any 2D or 3D body pose ground-truth. The proposed loss functions make use of the multiple-view geometry to reconstruct 3D body pose estimates and impose body pose constraints across the camera views. Our approach utilizes all available camera views during training, while the inference is s…
Indian Institute of Science（印度科学学院）；Google Research（谷歌研究院）
Camera captured human pose is an outcome of several sources of variation. Performance of supervised 3D pose estimation approaches comes at the cost of dispensing with variations, such as shape and appearance, that may be useful for solving other related tasks. As a result, the learned model not only inculcates task-bias but also dataset-bias because of its strong reliance on the annotated samples, which also holds true for weakly-supervised models. Acknowledging this, we propose a self-supervised learning framework to disentangle such variations from unlabeled video frames. We leverage the pri…
To obtain 3D annotations, we are restricted to controlled environments or synthetic datasets, leading us to 3D datasets with less generalizability to real-world scenarios. To tackle this issue in the context of semi-supervised 3D hand shape and pose estimation, we propose the Pose Alignment network to propagate 3D annotations from labelled frames to nearby unlabelled frames in sparsely annotated videos. We show that incorporating the alignment supervision on pairs of labelled-unlabelled frames allows us to improve the pose estimation accuracy. Besides, we show that the proposed Pose Alignment …
Shanghai Jiao Tong University（上海交通大学）；UC San Diego（加州大学圣地亚哥分校）
We propose to personalize a human pose estimator given a set of test images of a person without using any manual annotations. While there is a significant advancement in human pose estimation, it is still very challenging for a model to generalize to different unknown environments and unseen persons. Instead of using a fixed model for every test case, we adapt our pose estimator during test time to exploit person-specific information. We first train our model on diverse data with both a supervised and a self-supervised pose estimation objectives jointly. We use a Transformer model to build a t…
We address the problem of 3D human pose estimation from 2D input images using only weakly supervised training data. Despite showing considerable success for 2D pose estimation, the application of supervised machine learning to 3D pose estimation in real world images is currently hampered by the lack of varied training images with corresponding 3D poses. Most existing 3D pose estimation algorithms train on data that has either been collected in carefully controlled studio settings or has been generated synthetically. Instead, we take a different approach, and propose a 3D human pose estimation …
SNUAILAB（首尔大学人工智能实验室）；Seoul National University（首尔国立大学）
A well-designed strong-weak augmentation strategy and the stable teacher to generate reliable pseudo labels are essential in the teacher-student framework of semi-supervised learning (SSL). Considering these in mind, to suit the semi-supervised human pose estimation (SSHPE) task, we propose a novel approach referred to as Pose-MUM that modifies Mix/UnMix (MUM) augmentation. Like MUM in the dense prediction task, the proposed Pose-MUM makes strong-weak augmentation for pose estimation and leads the network to learn the relationship between each human key point much better than the conventional …
Cooperative Medianet Innovation Center, Shanghai Jiao Tong University（上海交通大学协同媒体网络创新中心）
3D hand-object pose estimation is an important issue to understand the interaction between human and environment. Current hand-object pose estimation methods require detailed 3D labels, which are expensive and labor-intensive. To tackle the problem of data collection, we propose a semi-supervised 3D hand-object pose estimation method with two key techniques: pose dictionary learning and an object-oriented coordinate system. The proposed pose dictionary learning module can distinguish infeasible poses by reconstruction error, enabling unlabeled data to provide supervision signals. The proposed …
Indian Institute of Technology Gandhinagar（印度理工学院甘地纳加尔分校）；Indian Institute of Technology Bhilai（印度理工学院比莱分校）
Impact craters are formed due to continuous impacts on the surface of planetary bodies. Most recent deep learning-based crater detection methods treat craters as circular shapes, and less attention is paid to extracting the exact shapes of craters. Extracting precise shapes of the craters can be helpful for many advanced analyses, such as crater formation. This paper proposes a combination of unsupervised non-deep learning and semi-supervised deep learning approach to accurately extract shapes of the craters and detect missing craters from the existing catalog. In unsupervised non-deep learnin…
Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；Intel Labs（英特尔实验室）
We address the problem of learning accurate 3D shape and camera pose from a collection of unlabeled category-specific images. We train a convolutional network to predict both the shape and the pose from a single image by minimizing the reprojection error: given several views of an object, the projections of the predicted shapes to the predicted camera poses should match the provided views. To deal with pose ambiguity, we introduce an ensemble of pose predictors which we then distill to a single "student" model. To allow for efficient learning of high-fidelity shapes, we represent the shapes by…
Training accurate 3D human pose estimators requires large amount of 3D ground-truth data which is costly to collect. Various weakly or self supervised pose estimation methods have been proposed due to lack of 3D data. Nevertheless, these methods, in addition to 2D ground-truth poses, require either additional supervision in various forms (e.g. unpaired 3D ground truth data, a small subset of labels) or the camera parameters in multiview settings. To address these problems, we present EpipolarPose, a self-supervised learning method for 3D human pose estimation, which does not need any 3D ground…
Estimating 3d human pose from monocular images is a challenging problem due to the variety and complexity of human poses and the inherent ambiguity in recovering depth from the single view. Recent deep learning based methods show promising results by using supervised learning on 3d pose annotated datasets. However, the lack of large-scale 3d annotated training data captured under in-the-wild settings makes the 3d pose estimation difficult for in-the-wild poses. Few approaches have utilized training images from both 3d and 2d pose datasets in a weakly-supervised manner for learning 3d poses in …
Tampere University（坦佩雷大学）；University of Oulu（奥卢大学）
Acquiring labeled 6D poses from real images is an expensive and time-consuming task. Though massive amounts of synthetic RGB images are easy to obtain, the models trained on them suffer from noticeable performance degradation due to the synthetic-to-real domain gap. To mitigate this degradation, we propose a practical self-supervised domain adaptation approach that takes advantage of real RGB(-D) data without needing real pose labels. We first pre-train the model with synthetic RGB images and then utilize real RGB(-D) images to fine-tune the pre-trained model. The fine-tuning process is self-s…
Facebook AI Research（Facebook人工智能研究院）；Université de Lyon（里昂大学）；INSA-Lyon（里昂国立应用科学学院）；CNRS（法国国家科学研究中心）；LIRIS（里昂信息、图像与信息系统实验室）；Awabot SAS（Awabot公司）；University of Guelph（圭尔夫大学）
We propose a method for hand pose estimation based on a deep regressor trained on two different kinds of input. Raw depth data is fused with an intermediate representation in the form of a segmentation of the hand into parts. This intermediate representation contains important topological information and provides useful cues for reasoning about joint locations. The mapping from raw depth to segmentation maps is learned in a semi/weakly-supervised way from two different datasets: (i) a synthetic dataset created through a rendering pipeline including densely labeled ground truth (pixelwise segme…
PosePilot: Steering Camera Pose for Generative World Models with Self-supervised Depth
The Hong Kong University of Science and Technology（香港科技大学）；Institute for AI Industry Research (AIR), Tsinghua University（清华大学人工智能产业研究院）；Li Auto；BAAI（北京人工智能研究院）
State-of-the-art approaches for 6D object pose estimation require large amounts of labeled data to train the deep networks. However, the acquisition of 6D object pose annotations is tedious and labor-intensive in large quantity. To alleviate this problem, we propose a weakly supervised 6D object pose estimation approach based on 2D keypoint detection. Our method trains only on image pairs with known relative transformations between their viewpoints. Specifically, we assign a set of arbitrarily chosen 3D keypoints to represent each unknown target 3D object and learn a network to detect their 2D…
Estimating 3D human poses from video is a challenging problem. The lack of 3D human pose annotations is a major obstacle for supervised training and for generalization to unseen datasets. In this work, we address this problem by proposing a weakly-supervised training scheme that does not require 3D annotations or calibrated cameras. The proposed method relies on temporal information and triangulation. Using 2D poses from multiple views as the input, we first estimate the relative camera orientations and then generate 3D poses via triangulation. The triangulation is only applied to the views wi…
Intraoperative shape reconstruction of organs from endoscopic camera images is a complex yet indispensable technique for image-guided surgery. To address the uncertainty in reconstructing entire shapes from single-viewpoint occluded images, we propose a framework for generative virtual learning of shape reconstruction using image translation with common latent variables between simulated and real images. As it is difficult to prepare sufficient amount of data to learn the relationship between endoscopic images and organ shapes, self-supervised virtual learning is performed using simulated imag…
We present a novel data-driven regularizer for weakly-supervised learning of 3D human pose estimation that eliminates the drift problem that affects existing approaches. We do this by moving the stereo reconstruction problem into the loss of the network itself. This avoids the need to reconstruct 3D data prior to training and unlike previous semi-supervised approaches, avoids the need for a warm-up period of supervised training. The conceptual and implementational simplicity of our approach is fundamental to its appeal. Not only is it straightforward to augment many weakly-supervised approache…
Virginia Tech（弗吉尼亚理工大学）；Peking University（北京大学）；Tsinghua University（清华大学）；Stanford University（斯坦福大学）；Columbia University（哥伦比亚大学）
Category-level object pose estimation aims to find 6D object poses of previously unseen object instances from known categories without access to object CAD models. To reduce the huge amount of pose annotations needed for category-level learning, we propose for the first time a self-supervised learning framework to estimate category-level 6D object pose from single 3D point clouds.During training, our method assumes no ground-truth pose annotations, no CAD models, and no multi-view supervision. The key to our method is to disentangle shape and pose through an invariant shape reconstruction modu…
University of British Columbia（不列颠哥伦比亚大学）；University of Victoria（维多利亚大学）；University of Toronto（多伦多大学）；Google Research（谷歌研究院）
We propose a self-supervised capsule architecture for 3D point clouds. We compute capsule decompositions of objects through permutation-equivariant attention, and self-supervise the process by training with pairs of randomly rotated objects. Our key idea is to aggregate the attention masks into semantic keypoints, and use these to supervise a decomposition that satisfies the capsule invariance/equivariance properties. This not only enables the training of a semantically consistent decomposition, but also allows us to learn a canonicalization operation that enables object-centric reasoning. To …
We propose to learn a 3D pose estimator by distilling knowledge from Non-Rigid Structure from Motion (NRSfM). Our method uses solely 2D landmark annotations. No 3D data, multi-view/temporal footage, or object specific prior is required. This alleviates the data bottleneck, which is one of the major concern for supervised methods. The challenge for using NRSfM as teacher is that they often make poor depth reconstruction when the 2D projections have strong ambiguity. Directly using those wrong depth as hard target would negatively impact the student. Instead, we propose a novel loss that ties de…
University of California, Irvine（加州大学尔湾分校）；Tencent America（腾讯美国）；Amazon（亚马逊）；National Chiao Tung University（国立交通大学）
Estimating 3D hand pose directly from RGB imagesis challenging but has gained steady progress recently bytraining deep models with annotated 3D poses. Howeverannotating 3D poses is difficult and as such only a few 3Dhand pose datasets are available, all with limited samplesizes. In this study, we propose a new framework of training3D pose estimation models from RGB images without usingexplicit 3D annotations, i.e., trained with only 2D informa-tion. Our framework is motivated by two observations: 1)Videos provide richer information for estimating 3D posesas opposed to static images; 2) Estimat…
IIT Bombay（印度理工学院孟买分校）；Axogyan AI（Axogyan人工智能公司）；IISc Bangalore（印度科学学院班加罗尔分校）；University of California, San Diego（加州大学圣地亚哥分校）
The best performing methods for 3D human pose estimation from monocular images require large amounts of in-the-wild 2D and controlled 3D pose annotated datasets which are costly and require sophisticated systems to acquire. To reduce this annotation dependency, we propose Multiview-Consistent Semi Supervised Learning (MCSS) framework that utilizes similarity in pose information from unannotated, uncalibrated but synchronized multi-view videos of human motions as additional weak supervision signal to guide 3D human pose regression. Our framework applies hard-negative mining based on temporal re…
Modern deep learning-based 3D pose estimation approaches require plenty of 3D pose annotations. However, existing 3D datasets lack diversity, which limits the performance of current methods and their generalization ability. Although existing methods utilize 2D pose annotations to help 3D pose estimation, they mainly focus on extracting 2D structural constraints from 2D poses, ignoring the 3D information hidden in the images. In this paper, we propose a novel method to extract weak 3D information directly from 2D images without 3D pose supervision. Firstly, we utilize 2D pose annotations and pe…
ETH Zürich（苏黎世联邦理工学院）；Facebook AI Research（脸书人工智能研究院）；Google Brain（谷歌大脑）
In this work, we demonstrate that 3D poses in video can be effectively estimated with a fully convolutional model based on dilated temporal convolutions over 2D keypoints. We also introduce back-projection, a simple and effective semi-supervised training method that leverages unlabeled video data. We start with predicted 2D keypoints for unlabeled video, then estimate 3D poses and finally back-project to the input 2D keypoints. In the supervised setting, our fully-convolutional model outperforms the previous best result from the literature by 6 mm mean per-joint position error on Human3.6M, co…
Category-level articulated object pose estimation aims to estimate a hierarchy of articulation-aware object poses of an unseen articulated object from a known category. To reduce the heavy annotations needed for supervised learning methods, we present a novel self-supervised strategy that solves this problem without any human labels. Our key idea is to factorize canonical shapes and articulated object poses from input articulated shapes through part-level equivariant shape analysis. Specifically, we first introduce the concept of part-level SE(3) equivariance and devise a network to learn feat…
Beijing University of Posts and Telecommunications（北京邮电大学）；Beike（贝壳）
In this paper, we delve into semi-supervised 2D human pose estimation. The previous method ignored two problems: (i) When conducting interactive training between large model and lightweight model, the pseudo label of lightweight model will be used to guide large models. (ii) The negative impact of noise pseudo labels on training. Moreover, the labels used for 2D human pose estimation are relatively complex: keypoint category and keypoint position. To solve the problems mentioned above, we propose a semi-supervised 2D human pose estimation framework driven by a position inconsistency pseudo lab…
Monocular 3D human pose and shape estimation is challenging due to the many degrees of freedom of the human body and thedifficulty to acquire training data for large-scale supervised learning in complex visual scenes. In this paper we present practical semi-supervised and self-supervised models that support training and good generalization in real-world images and video. Our formulation is based on kinematic latent normalizing flow representations and dynamics, as well as differentiable, semantic body part alignment loss functions that support self-supervised learning. In extensive experiments…
The current state-of-the-art in monocular 3D human pose estimation is heavily influenced by weakly supervised methods. These allow 2D labels to be used to learn effective 3D human pose recovery either directly from images or via 2D-to-3D pose uplifting. In this paper we present a detailed analysis of the most commonly used simplified projection models, which relate the estimated 3D pose representation to 2D labels: normalized perspective and weak perspective projections. Specifically, we derive theoretical lower bound errors for those projection models under the commonly used mean per-joint po…
Imperial College London（帝国理工学院）；Niantic（尼安蒂克）；KAIST（韩国科学技术院）
Most successful approaches to estimate the 6D pose of an object typically train a neural network by supervising the learning with annotated poses in real world images. These annotations are generally expensive to obtain and a common workaround is to generate and train on synthetic scenes, with the drawback of limited generalisation when the model is deployed in the real world. In this work, a two-stage 6D object pose estimator framework that can be applied on top of existing neural-network-based approaches and that does not require pose annotations on real images is proposed. The first self-su…
Technical University of Munich（慕尼黑工业大学）；Tsinghua University（清华大学）；Google（谷歌）
6D object pose estimation is a fundamental problem in computer vision. Convolutional Neural Networks (CNNs) have recently proven to be capable of predicting reliable 6D pose estimates even from monocular images. Nonetheless, CNNs are identified as being extremely data-driven, and acquiring adequate annotations is oftentimes very time-consuming and labor intensive. To overcome this shortcoming, we propose the idea of monocular 6D pose estimation by means of self-supervised learning, removing the need for real annotations. After training our proposed network fully supervised with synthetic RGB d…
Carl Zeiss Meditec AG（卡尔蔡司医疗科技公司）；Technical University of Munich（慕尼黑工业大学）
For many practical problems and applications, it is not feasible to create a vast and accurately labeled dataset, which restricts the application of deep learning in many areas. Semi-supervised learning algorithms intend to improve performance by also leveraging unlabeled data. This is very valuable for 2D-pose estimation task where data labeling requires substantial time and is subject to noise. This work aims to investigate if semi-supervised learning techniques can achieve acceptable performance level that makes using these algorithms during training justifiable. To this end, a lightweight …
University of Rochester（罗切斯特大学）；Google Inc.（谷歌公司）；ByteDance AI Lab（字节跳动人工智能实验室）；Vaitl Inc.（维特尔公司）
Human body part segmentation refers to the task of predicting the semantic segmentation mask for each body part. Fully supervised body part segmentation methods achieve good performances but require an enormous amount of effort to annotate part masks for training. In contrast to high annotation costs needed for a limited number of part mask annotations, a large number of weak labels such as poses and full body masks already exist and contain relevant information. Motivated by the possibility of using existing weak labels, we propose the first weakly supervised body part segmentation framework.…
Current state-of-the-art methods cast monocular 3D human pose estimation as a learning problem by training neural networks on large data sets of images and corresponding skeleton poses. In contrast, we propose an approach that can exploit small annotated data sets by fine-tuning networks pre-trained via self-supervised learning on (large) unlabeled data sets. To drive such networks towards supporting 3D pose estimation during the pre-training step, we introduce a novel self-supervised feature learning task designed to focus on the 3D structure in an image. We exploit images extracted from vide…
LIGM（信息学实验室加斯东·贝杰）；Ecole des Ponts（巴黎高科路桥学院）；Univ Gustave Eiffel（古斯塔夫·埃菲尔大学）；CNRS（法国国家科学研究中心）
There has been recently a growing interest for implicit shape representations. Contrary to explicit representations, they have no resolution limitations and they easily deal with a wide variety of surface topologies. To learn these implicit representations, current approaches rely on a certain level of shape supervision (e.g., inside/outside information or distance-to-shape knowledge), or at least require a dense point cloud (to approximate well enough the distance-to-shape). In contrast, we introduce NeeDrop, a self-supervised method for learning shape representations from possibly extremely …
University of California, Merced（加州大学默塞德分校）；Google Research（谷歌研究院）；Indian Institute of Science（印度科学学院）
Reconstructing 3D models from 2D images is one of the fundamental problems in computer vision. In this work, we propose a deep learning technique for 3D object reconstruction from a single image. Contrary to recent works that either use 3D supervision or multi-view supervision, we use only single view images with no pose information during training as well. This makes our approach more practical requiring only an image collection of an object category and the corresponding silhouettes. We learn both 3D point cloud reconstruction and pose estimation networks in a self-supervised manner, making …
