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 relations in multi-view videos to arrive at a multi-view consistent pose embedding. When jointly trained with limited 3D pose annotations, our approach improves the baseline by 25% and state-of-the-art by 8.7%, whilst using substantially smaller networks. Lastly, but importantly, we demonstrate the advantages of the learned embedding and establish view-invariant pose retrieval benchmarks on two popular, publicly available multi-view human pose datasets, Human 3.6M and MPI-INF-3DHP, to facilitate future research.
This paper presents MONET -- an end-to-end semi-supervised learning framework for a keypoint detector using multiview image streams. In particular, we consider general subjects such as non-human species where attaining a large scale annotated dataset is challenging. While multiview geometry can be used to self-supervise the unlabeled data, integrating the geometry into learning a keypoint detector is challenging due to representation mismatch. We address this mismatch by formulating a new differentiable representation of the epipolar constraint called epipolar divergence---a generalized distan…
Southeast University（东南大学）；Microsoft Research Asia（微软亚洲研究院）；The Johns Hopkins University（约翰斯·霍普金斯大学）
Occlusion is probably the biggest challenge for human pose estimation in the wild. Typical solutions often rely on intrusive sensors such as IMUs to detect occluded joints. To make the task truly unconstrained, we present AdaFuse, an adaptive multiview fusion method, which can enhance the features in occluded views by leveraging those in visible views. The core of AdaFuse is to determine the point-point correspondence between two views which we solve effectively by exploring the sparsity of the heatmap representation. We also learn an adaptive fusion weight for each camera view to reflect its …
This paper presents a semi-supervised learning framework for a customized semantic segmentation task using multiview image streams. A key challenge of the customized task lies in the limited accessibility of the labeled data due to the requirement of prohibitive manual annotation effort. We hypothesize that it is possible to leverage multiview image streams that are linked through the underlying 3D geometry, which can provide an additional supervisionary signal to train a segmentation model. We formulate a new cross-supervision method using a shape belief transfer---the segmentation belief in …
Multiview recognition has been well studied in the literature and achieves decent performance in object recognition and retrieval task. However, most previous works rely on supervised learning and some impractical underlying assumptions, such as the availability of all views in training and inference time. In this work, the problem of multiview self-supervised learning (MV-SSL) is investigated, where only image to object association is given. Given this setup, a novel surrogate task for self-supervised learning is proposed by pursuing "object invariant" representation. This is solved by random…
We propose an efficient approach to exploiting motion information from consecutive frames of a video sequence to recover the 3D pose of people. Previous approaches typically compute candidate poses in individual frames and then link them in a post-processing step to resolve ambiguities. By contrast, we directly regress from a spatio-temporal volume of bounding boxes to a 3D pose in the central frame. We further show that, for this approach to achieve its full potential, it is essential to compensate for the motion in consecutive frames so that the subject remains centered. This then allows us …
Video provides us with the spatio-temporal consistency needed for visual learning. Recent approaches have utilized this signal to learn correspondence estimation from close-by frame pairs. However, by only relying on close-by frame pairs, those approaches miss out on the richer long-range consistency between distant overlapping frames. To address this, we propose a self-supervised approach for correspondence estimation that learns from multiview consistency in short RGB-D video sequences. Our approach combines pairwise correspondence estimation and registration with a novel SE(3) transformatio…
University of Science and Technology of China（中国科学技术大学）；Microsoft Research Asia（微软亚洲研究院）；TuSimple（图森未来）
We present an approach to recover absolute 3D human poses from multi-view images by incorporating multi-view geometric priors in our model. It consists of two separate steps: (1) estimating the 2D poses in multi-view images and (2) recovering the 3D poses from the multi-view 2D poses. First, we introduce a cross-view fusion scheme into CNN to jointly estimate 2D poses for multiple views. Consequently, the 2D pose estimation for each view already benefits from other views. Second, we present a recursive Pictorial Structure Model to recover the 3D pose from the multi-view 2D poses. It gradually …
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…
In recent years self-supervised learning has emerged as a promising candidate for unsupervised representation learning. In the visual domain its applications are mostly studied in the context of images of natural scenes. However, its applicability is especially interesting in specific areas, like remote sensing and medicine, where it is hard to obtain huge amounts of labeled data. In this work, we conduct an extensive analysis of the applicability of self-supervised learning in remote sensing image classification. We analyze the influence of the number and domain of images used for self-superv…
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 …
Naval Aeronautical and Astronautical University（海军航空航天大学）；Ryerson University（瑞尔森大学）；Ludong University（鲁东大学）
Multiview learning problem refers to the problem of learning a classifier from multiple view data. In this data set, each data points is presented by multiple different views. In this paper, we propose a novel method for this problem. This method is based on two assumptions. The first assumption is that each data point has an intact feature vector, and each view is obtained by a linear transformation from the intact vector. The second assumption is that the intact vectors are discriminative, and in the intact space, we have a linear classifier to separate the positive class from the negative c…
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…
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 …
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…
Nanjing University of Information Science and Technology（南京信息工程大学）
This paper proposes a unified framework dubbed Multi-view and Temporal Fusing Transformer (MTF-Transformer) to adaptively handle varying view numbers and video length without camera calibration in 3D Human Pose Estimation (HPE). It consists of Feature Extractor, Multi-view Fusing Transformer (MFT), and Temporal Fusing Transformer (TFT). Feature Extractor estimates 2D pose from each image and fuses the prediction according to the confidence. It provides pose-focused feature embedding and makes subsequent modules computationally lightweight. MFT fuses the features of a varying number of views wi…
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…
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…
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…
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…
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…
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.…
Univ. of California Santa Barbara（加州大学圣巴巴拉分校）；West Virginia University（西弗吉尼亚大学）；Santa Barbara Cottage Hospital（圣巴巴拉 Cottage 医院）
Manual analysis of body poses of bed-ridden patients requires staff to continuously track and record patient poses. Two limitations in the dissemination of pose-related therapies are scarce human resources and unreliable automated systems. This work addresses these issues by introducing a new method and a new system for robust automated classification of sleep poses in an Intensive Care Unit (ICU) environment. The new method, coupled-constrained Least-Squares (cc-LS), uses multimodal and multiview (MM) data and finds the set of modality trust values that minimizes the difference between expect…
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…
We present a multiview pseudo-labeling approach to video learning, a novel framework that uses complementary views in the form of appearance and motion information for semi-supervised learning in video. The complementary views help obtain more reliable pseudo-labels on unlabeled video, to learn stronger video representations than from purely supervised data. Though our method capitalizes on multiple views, it nonetheless trains a model that is shared across appearance and motion input and thus, by design, incurs no additional computation overhead at inference time. On multiple video recognitio…
University of Pennsylvania（宾夕法尼亚大学）；University of Minnesota（明尼苏达大学）
This paper presents a semi-supervised learning framework to train a keypoint detector using multiview image streams given the limited labeled data (typically $<$4\%). We leverage the complementary relationship between multiview geometry and visual tracking to provide three types of supervisionary signals to utilize the unlabeled data: (1) keypoint detection in one view can be supervised by other views via the epipolar geometry; (2) a keypoint moves smoothly over time where its optical flow can be used to temporally supervise consecutive image frames to each other; (3) visible keypoint in one v…
National Institute of Advanced Industrial Science and Technology (AIST)（国立先进工业科学技术研究所（AIST））；Graduate School of Information Science and Technology, Osaka University（大阪大学信息科学与技术研究生院）
We propose a Convolutional Neural Network (CNN)-based model "RotationNet," which takes multi-view images of an object as input and jointly estimates its pose and object category. Unlike previous approaches that use known viewpoint labels for training, our method treats the viewpoint labels as latent variables, which are learned in an unsupervised manner during the training using an unaligned object dataset. RotationNet is designed to use only a partial set of multi-view images for inference, and this property makes it useful in practical scenarios where only partial views are available. Moreov…
Accurate hand pose estimation at joint level has several uses on human-robot interaction, user interfacing and virtual reality applications. Yet, it currently is not a solved problem. The novel deep learning techniques could make a great improvement on this matter but they need a huge amount of annotated data. The hand pose datasets released so far present some issues that make them impossible to use on deep learning methods such as the few number of samples, high-level abstraction annotations or samples consisting in depth maps. In this work, we introduce a multiview hand pose dataset in whic…
Multiview self-supervised representation learning roots in exploring semantic consistency across data of complex intra-class variation. Such variation is not directly accessible and therefore simulated by data augmentations. However, commonly adopted augmentations are handcrafted and limited to simple geometrical and color changes, which are unable to cover the abundant intra-class variation. In this paper, we propose to extract the underlying data variation from datasets and construct a novel augmentation operator, named local manifold augmentation (LMA). LMA is achieved by training an instan…
We present a method to combine markerless motion capture and dense pose feature estimation into a single framework. We demonstrate that dense pose information can help for multiview/single-view motion capture, and multiview motion capture can help the collection of a high-quality dataset for training the dense pose detector. Specifically, we first introduce a novel markerless motion capture method that can take advantage of dense parsing capability provided by the dense pose detector. Thanks to the introduced dense human parsing ability, our method is demonstrated much more efficient, and accu…
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,…
University of Rochester（罗切斯特大学）；University of Maryland, College Park（马里兰大学帕克分校）；Rutgers University（罗格斯大学）；Z2W Corporation（Z2W公司）；Chinese Academy of Sciences（中国科学院）；Peng Cheng Laboratory（鹏城实验室）
We propose to tackle the problem of multiview 2D/3D rigid registration for intervention via a Point-Of-Interest Network for Tracking and Triangulation ($\text{POINT}^2$). $\text{POINT}^2$ learns to establish 2D point-to-point correspondences between the pre- and intra-intervention images by tracking a set of random POIs. The 3D pose of the pre-intervention volume is then estimated through a triangulation layer. In $\text{POINT}^2$, the unified framework of the POI tracker and the triangulation layer enables learning informative 2D features and estimating 3D pose jointly. In contrast to existin…
In this paper we show how to perform scene-level inverse rendering to recover shape, reflectance and lighting from a single, uncontrolled image using a fully convolutional neural network. The network takes an RGB image as input, regresses albedo, shadow and normal maps from which we infer least squares optimal spherical harmonic lighting coefficients. Our network is trained using large uncontrolled multiview and timelapse image collections without ground truth. By incorporating a differentiable renderer, our network can learn from self-supervision. Since the problem is ill-posed we introduce a…
University of California Santa Barbara（加州大学圣巴巴拉分校）；Santa Barbara Cottage Hospital（圣巴巴拉村舍医院）
Clinical observations indicate that during critical care at the hospitals, patients sleep positioning and motion affect recovery. Unfortunately, there is no formal medical protocol to record, quantify, and analyze patient motion. There is a small number of clinical studies, which use manual analysis of sleep poses and motion recordings to support medical benefits of patient positioning and motion monitoring. Manual processes are not scalable, are prone to human errors, and strain an already taxed healthcare workforce. This study introduces DECU (Deep Eye-CU): an autonomous mulitmodal multiview…
Multiview camera setups have proven useful in many computer vision applications for reducing ambiguities, mitigating occlusions, and increasing field-of-view coverage. However, the high computational cost associated with multiple views poses a significant challenge for end devices with limited computational resources. To address this issue, we propose a view selection approach that analyzes the target object or scenario from given views and selects the next best view for processing. Our approach features a reinforcement learning based camera selection module, MVSelect, that not only selects vi…
