Deep learning-based 3D human pose estimation performs best when trained on large amounts of labeled data, making combined learning from many datasets an important research direction. One obstacle to this endeavor are the different skeleton formats provided by different datasets, i.e., they do not label the same set of anatomical landmarks. There is little prior research on how to best supervise one model with such discrepant labels. We show that simply using separate output heads for different skeletons results in inconsistent depth estimates and insufficient information sharing across skeletons. As a remedy, we propose a novel affine-combining autoencoder (ACAE) method to perform dimensionality reduction on the number of landmarks. The discovered latent 3D points capture the redundancy among skeletons, enabling enhanced information sharing when used for consistency regularization. Our approach scales to an extreme multi-dataset regime, where we use 28 3D human pose datasets to supervise one model, which outperforms prior work on a range of benchmarks, including the challenging 3D Poses in the Wild (3DPW) dataset. Our code and models are available for research purposes.

大多数实时人类姿势估计方法都基于检测接头位置。使用检测到的关节位置，可以计算偏差和肢体的俯仰。然而，由于这种旋转轴仍然不观察，因此不能计算沿着肢体沿着肢体至关重要的曲折，这对于诸如体育分析和计算机动画至关重要。在本文中，我们引入了方向关键点，一种用于估计骨骼关节的全位置和旋转的新方法，仅使用单帧RGB图像。灵感来自Motion-Capture Systems如何使用一组点标记来估计全骨骼旋转，我们的方法使用虚拟标记来生成足够的信息，以便准确地推断使用简单的后处理。旋转预测改善了接头角度最佳报告的平均误差48％，并且在15个骨骼旋转中实现了93％的精度。该方法还通过MPJPE在原理数据集上测量，通过MPJPE测量，该方法还改善了当前的最新结果14％，并概括为野外数据集。

3D models provide a common ground for different representations of human bodies. In turn, robust 2D estimation has proven to be a powerful tool to obtain 3D fits "in-thewild". However, depending on the level of detail, it can be hard to impossible to acquire labeled data for training 2D estimators on large scale. We propose a hybrid approach to this problem: with an extended version of the recently introduced SMPLify method, we obtain high quality 3D body model fits for multiple human pose datasets. Human annotators solely sort good and bad fits. This procedure leads to an initial dataset, UP-3D, with rich annotations. With a comprehensive set of experiments, we show how this data can be used to train discriminative models that produce results with an unprecedented level of detail: our models predict 31 segments and 91 landmark locations on the body. Using the 91 landmark pose estimator, we present state-ofthe art results for 3D human pose and shape estimation using an order of magnitude less training data and without assumptions about gender or pose in the fitting procedure. We show that UP-3D can be enhanced with these improved fits to grow in quantity and quality, which makes the system deployable on large scale. The data, code and models are available for research purposes.* This work was performed while J. Romero and F. Bogo were with the MPI-IS 2 ; P. V. Gehler with the BCCN 1 and MPI-IS 2 .

Figure 1: Given challenging in-the-wild videos, a recent state-of-the-art video-pose-estimation approach [31] (top), fails to produce accurate 3D body poses. To address this, we exploit a large-scale motion-capture dataset to train a motion discriminator using an adversarial approach. Our model (VIBE) (bottom) is able to produce realistic and accurate pose and shape, outperforming previous work on standard benchmarks.

Input Reconstruction Side and top down view Part Segmentation Input Reconstruction Side and top down view Part Segmentation Figure 1: Human Mesh Recovery (HMR): End-to-end adversarial learning of human pose and shape. We describe a real time framework for recovering the 3D joint angles and shape of the body from a single RGB image. The first two rowsshow results from our model trained with some 2D-to-3D supervision, the bottom row shows results from a model that is trained in a fully weakly-supervised manner without using any paired 2D-to-3D supervision. We infer the full 3D body even in case of occlusions and truncations. Note that we capture head and limb orientations.

全面监督的人类网格恢复方法是渴望数据的，由于3D规定基准数据集的可用性有限和多样性，因此具有较差的概括性。使用合成数据驱动的训练范例，已经从合成配对的2D表示（例如2D关键点和分段掩码）和3D网格中训练了模型的最新进展，其中已使用合成数据驱动的训练范例和3D网格进行了训练。但是，由于合成训练数据和实际测试数据之间的域间隙很难解决2D密集表示，因此很少探索合成密集的对应图（即IUV）。为了减轻IUV上的这个领域差距，我们提出了使用可靠但稀疏表示的互补信息（2D关键点）提出的交叉代理对齐。具体而言，初始网格估计和两个2D表示之间的比对误差将转发为回归器，并在以下网格回归中动态校正。这种适应性的交叉代理对准明确地从偏差和捕获互补信息中学习：从稀疏的表示和浓郁的浓度中的稳健性。我们对多个标准基准数据集进行了广泛的实验，并展示了竞争结果，帮助减少在人类网格估计中生产最新模型所需的注释工作。

了解来自第一人称观点的社交互动对于许多应用来说至关重要，从辅助机器人到AR / VR。谈论相互作用的第一步是理解人类的姿势和形状。但是，该领域的研究目前受到数据缺乏的阻碍。现有数据集根据大小，注释，地面真实捕获方式或相互作用的多样性有限。我们通过提出EGOBODY来解决这一缺点，这是一个用于复杂3D场景中的社交交互的新型大规模数据集。我们采用Microsoft Hololens2耳机来记录富裕的EGEntric数据流（包括RGB，深度，眼睛凝视，头部和手动跟踪）。为了获得准确的3D地面真理，我们将耳机用多kinect钻机校准并配合富有呈现的SMPL-X体网格到多视图RGB-D帧，重建3D人类姿势和相对于场景的形状。我们收集68个序列，跨越不同的社会学互动类别，并提出了从自我监视视图的3D全体姿态和形状估计的第一个基准。我们的数据集和代码将在https://sanweiliti.github.io/egobody/egobody.html中进行研究。

This work addresses the problem of estimating the full body 3D human pose and shape from a single color image. This is a task where iterative optimization-based solutions have typically prevailed, while Convolutional Networks (ConvNets) have suffered because of the lack of training data and their low resolution 3D predictions. Our work aims to bridge this gap and proposes an efficient and effective direct prediction method based on ConvNets. Central part to our approach is the incorporation of a parametric statistical body shape model (SMPL) within our end-to-end framework. This allows us to get very detailed 3D mesh results, while requiring estimation only of a small number of parameters, making it friendly for direct network prediction. Interestingly, we demonstrate that these parameters can be predicted reliably only from 2D keypoints and masks. These are typical outputs of generic 2D human analysis ConvNets, allowing us to relax the massive requirement that images with 3D shape ground truth are available for training. Simultaneously, by maintaining differentiability, at training time we generate the 3D mesh from the estimated parameters and optimize explicitly for the surface using a 3D per-vertex loss. Finally, a differentiable renderer is employed to project the 3D mesh to the image, which enables further refinement of the network, by optimizing for the consistency of the projection with 2D annotations (i.e., 2D keypoints or masks). The proposed approach outperforms previous baselines on this task and offers an attractive solution for direct prediction of 3D shape from a single color image.

当标记的数据丰富时，从单个图像中进行3D姿势估计的监督方法非常有效。但是，由于对地面3D标签的获取是劳动密集型且耗时的，最近的关注已转向半决赛和弱监督的学习。产生有效的监督形式，几乎没有注释，仍然在拥挤的场景中构成重大挑战。在本文中，我们建议通过加权区分三角剖分施加多视文几何约束，并在没有标签时将其用作一种自我设计的形式。因此，我们以一种方式训练2D姿势估计器，以使其预测对应于对三角姿势的3D姿势的重新投影，并在其上训练辅助网络以产生最终的3D姿势。我们通过一种加权机制来补充三角剖分，从而减轻了由自我咬合或其他受试者的遮挡引起的嘈杂预测的影响。我们证明了半监督方法对人类36M和MPI-INF-3DHP数据集的有效性，以及在具有闭塞的新的多视频多人数据集上。

人类性能捕获是一种非常重要的计算机视觉问题，在电影制作和虚拟/增强现实中具有许多应用。许多以前的性能捕获方法需要昂贵的多视图设置，或者没有恢复具有帧到帧对应关系的密集时空相干几何。我们提出了一种新颖的深度致密人体性能捕获的深层学习方法。我们的方法是基于多视图监督的弱监督方式培训，完全删除了使用3D地面真理注释的培训数据的需求。网络架构基于两个单独的网络，将任务解散为姿势估计和非刚性表面变形步骤。广泛的定性和定量评估表明，我们的方法在质量和稳健性方面优于现有技术。这项工作是DeepCAP的扩展版本，在那里我们提供更详细的解释，比较和结果以及应用程序。

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, corresponding to an error reduction of 11%, and the model also shows significant improvements on HumanEva-I. Moreover, experiments with back-projection show that it comfortably outperforms previous state-of-the-art results in semisupervised settings where labeled data is scarce. Code and models are available at https://github.com/ facebookresearch/VideoPose3D

We propose a CNN-based approach for 3D human body pose estimation from single RGB images that addresses the issue of limited generalizability of models trained solely on the starkly limited publicly available 3D pose data. Using only the existing 3D pose data and 2D pose data, we show state-of-the-art performance on established benchmarks through transfer of learned features, while also generalizing to in-the-wild scenes. We further introduce a new training set for human body pose estimation from monocular images of real humans that has the ground truth captured with a multi-camera marker-less motion capture system. It complements existing corpora with greater diversity in pose, human appearance, clothing, occlusion, and viewpoints, and enables an increased scope of augmentation. We also contribute a new benchmark that covers outdoor and indoor scenes, and demonstrate that our 3D pose dataset shows better in-the-wild performance than existing annotated data, which is further improved in conjunction with transfer learning from 2D pose data. All in all, we argue that the use of transfer learning of representations in tandem with algorithmic and data contributions is crucial for general 3D body pose estimation.

在本文中，我们考虑了同时找到和从单个2D图像中恢复多手的具有挑战性的任务。先前的研究要么关注单手重建，要么以多阶段的方式解决此问题。此外，常规的两阶段管道首先检测到手部区域，然后估计每个裁剪贴片的3D手姿势。为了减少预处理和特征提取中的计算冗余，我们提出了一条简洁但有效的单阶段管道。具体而言，我们为多手重建设计了多头自动编码器结构，每个HEAD网络分别共享相同的功能图并分别输出手动中心，姿势和纹理。此外，我们采用了一个弱监督的计划来减轻昂贵的3D现实世界数据注释的负担。为此，我们提出了一系列通过舞台训练方案优化的损失，其中根据公开可用的单手数据集生成具有2D注释的多手数据集。为了进一步提高弱监督模型的准确性，我们在单手和多个手设置中采用了几个功能一致性约束。具体而言，从本地功能估算的每只手的关键点应与全局功能预测的重新投影点一致。在包括Freihand，HO3D，Interhand 2.6M和RHD在内的公共基准测试的广泛实验表明，我们的方法在弱监督和完全监督的举止中优于基于最先进的模型方法。代码和模型可在{\ url {https://github.com/zijinxuxu/smhr}}上获得。

我们从单一的图像处理多的人三维人体姿势和体形估计的问题。虽然这个问题可以通过应用单人对同一场景接近多次来解决，近期的作品都示出的建筑在深深的架构，同时推理通过强制执行，例如，深度为了所有的人都在现场以整体方式的优点限制或重建的机构之间相互渗透最小化。但是，现有的方法仍然无法捕捉所造成的内在的体规模和深度的模糊人的规模变化。在这项工作中，我们处理的，通过强制所有的人的脚留在地面制定是学习的适当机构的规模和相对相机姿态新颖的优化方案，这一挑战。在MuPoTS-3D和3DPW数据集进行彻底的评估表明，我们的做法是能够稳健地估计多的人的身体翻译和形状，而取回自己的空间布置，始终如一改善当前国家的最先进的，尤其是在场面与人非常不同的高度

以准确的，稳健和快速的方式拟合人体，手或面对稀疏输入信号的参数模型，这具有重要的是在AR和VR场景中显着改善浸入。解决这些问题的系统中的一个常见的第一步是直接从输入数据重新分配参数模型的参数。这种方法是快速，稳健的，并且是迭代最小化算法的良好起点。后者搜索最小的能量函数，通常由编码关于问题的结构的知识的数据项和前沿组成。虽然这无疑是一个非常成功的食谱，但前锋往往是手工定义的启发式，发现不同术语之间的正确平衡，以实现高质量的结果是一个非琐碎的任务。此外，转换和优化这些系统以表现方式运行，需要定制实现，要求从工程师和域专家进行大量时间投资。在这项工作中，我们建立了近期学习优化的进步，并提出了由Classic Levenberg-Marquardt算法启发的更新规则。我们展示了所提出的神经优化器对从2D地标的头戴式装置和面部配件的3D体表估计问题的有效性。我们的方法可以很容易地应用于新的模型拟合问题，并提供竞争替代方案，在准确性和速度方面都提供了良好的调谐“传统”模型拟合管道。

对图像分类任务的对比学习成功的鼓励，我们为3D手姿势估计的结构化回归任务提出了一种新的自我监督方法。对比学习利用未标记的数据来通过损失制定来使用未标记的数据，以鼓励学习的特征表示在任何图像转换下都是不变的。对于3D手姿势估计，它也希望具有不变性地与诸如颜色抖动的外观变换。但是，该任务需要在仿射和转换之类的转换下的标准性。为了解决这个问题，我们提出了一种对比的对比目标，并在3D手姿势估计的背景下展示其有效性。我们通过实验研究了不变性和对比的对比目标的影响，并表明学习的等待特征导致3D手姿势估计的任务的更好表示。此外，我们显示具有足够深度的标准Evenet，在额外的未标记数据上培训，在弗雷手中获得高达14.5％的提高，因此在没有任何任务的专用架构的情况下实现最先进的性能。 https://ait.ethz.ch/projects/2021/peclr/使用代码和模型

3D human whole-body pose estimation aims to localize precise 3D keypoints on the entire human body, including the face, hands, body, and feet. Due to the lack of a large-scale fully annotated 3D whole-body dataset, a common approach has been to train several deep networks separately on datasets dedicated to specific body parts, and combine them during inference. This approach suffers from complex training and inference pipelines because of the different biases in each dataset used. It also lacks a common benchmark which makes it difficult to compare different methods. To address these issues, we introduce Human3.6M 3D WholeBody (H3WB) which provides whole-body annotations for the Human3.6M dataset using the COCO Wholebody layout. H3WB is a large scale dataset with 133 whole-body keypoint annotations on 100K images, made possible by our new multi-view pipeline. Along with H3WB, we propose 3 tasks: i) 3D whole-body pose lifting from 2D complete whole-body pose, ii) 3D whole-body pose lifting from 2D incomplete whole-body pose, iii) 3D whole-body pose estimation from a single RGB image. We also report several baselines from popular methods for these tasks. The dataset is publicly available at \url{https://github.com/wholebody3d/wholebody3d}.

This paper addresses the problem of 3D human pose and shape estimation from a single image. Previous approaches consider a parametric model of the human body, SMPL, and attempt to regress the model parameters that give rise to a mesh consistent with image evidence. This parameter regression has been a very challenging task, with modelbased approaches underperforming compared to nonparametric solutions in terms of pose estimation. In our work, we propose to relax this heavy reliance on the model's parameter space. We still retain the topology of the SMPL template mesh, but instead of predicting model parameters, we directly regress the 3D location of the mesh vertices. This is a heavy task for a typical network, but our key insight is that the regression becomes significantly easier using a Graph-CNN. This architecture allows us to explicitly encode the template mesh structure within the network and leverage the spatial locality the mesh has to offer. Image-based features are attached to the mesh vertices and the Graph-CNN is responsible to process them on the mesh structure, while the regression target for each vertex is its 3D location. Having recovered the complete 3D geometry of the mesh, if we still require a specific model parametrization, this can be reliably regressed from the vertices locations. We demonstrate the flexibility and the effectiveness of our proposed graphbased mesh regression by attaching different types of features on the mesh vertices. In all cases, we outperform the comparable baselines relying on model parameter regression, while we also achieve state-of-the-art results among model-based pose estimation approaches. 1

To facilitate the analysis of human actions, interactions and emotions, we compute a 3D model of human body pose, hand pose, and facial expression from a single monocular image. To achieve this, we use thousands of 3D scans to train a new, unified, 3D model of the human body, SMPL-X, that extends SMPL with fully articulated hands and an expressive face. Learning to regress the parameters of SMPL-X directly from images is challenging without paired images and 3D ground truth. Consequently, we follow the approach of SMPLify, which estimates 2D features and then optimizes model parameters to fit the features. We improve on SMPLify in several significant ways: (1) we detect 2D features corresponding to the face, hands, and feet and fit the full SMPL-X model to these; (2) we train a new neural network pose prior using a large MoCap dataset; (3) we define a new interpenetration penalty that is both fast and accurate; (4) we automatically detect gender and the appropriate body models (male, female, or neutral); (5) our PyTorch implementation achieves a speedup of more than 8× over Chumpy. We use the new method, SMPLify-X, to fit SMPL-X to both controlled images and images in the wild. We evaluate 3D accuracy on a new curated dataset comprising 100 images with pseudo ground-truth. This is a step towards automatic expressive human capture from monocular RGB data. The models, code, and data are available for research purposes at https://smpl-x.is.tue.mpg.de.

从单个图像中感知3D人体的能力具有多种应用，从娱乐和机器人技术到神经科学和医疗保健。人类网格恢复中的一个基本挑战是收集训练所需的地面真相3D网格目标，这需要负担重大的运动捕获系统，并且通常仅限于室内实验室。结果，尽管在这些限制性设置中收集的基准数据集上取得了进展，但由于分配变化，模型无法推广到现实世界中的``野外''方案。我们提出了域自适应3D姿势增强（DAPA），这是一种数据增强方法，可增强模型在野外场景中的概括能力。 DAPA通过从综合网格中获得直接监督，并通过使用目标数据集的地面真相2D关键点来结合基于合成数据集的方法的强度。我们定量地表明，使用DAPA的填充有效地改善了基准3DPW和Agora的结果。我们进一步证明了DAPA在一个充满挑战的数据集中，该数据集从现实世界中亲子互动的视频中策划了。