皮肤多人线性（SMPL）模型可以通过将姿势和形状参数映射到体网格来代表人体。已经示出了通过不同的学习模型方便推断3D人类姿势和形状。但是，并非所有的姿势和形状参数值都会产生物理合理的甚至现实的身体网格。换句话说，SMPL受到不受限制的，因此可以通过直接优化其参数来重建从图像的人类或通过从图像学习映射到这些参数来导致从图像中的人类来实现无效的结果。在本文中，我们学习之前将SMPL参数限制为通过对抗性培训产生现实姿势的值。我们表明，我们的学习了先前涵盖了实际数据分布的多样性，便于从2D关卡点进行3D重建的优化，并在用于从图像回归时产生更好的姿势估计。我们发现基于球面分布的先前获得了最佳效果。此外，在所有这些任务中，它优于基于最先进的VAE的方法来限制SMPL参数。

我们提出了姿势-NDF，这是基于神经距离场（NDFS）的合理人姿势的连续模型。姿势或运动先验对于产生现实的新姿势和重建噪音或部分观察的准确姿势很重要。 Pose-NDF学习了一个合理姿势的多种姿势作为神经隐式函数的零级集合，将3D中隐式表面建模的概念扩展到高维域So（3）^k，其中人姿势由A定义为一个由A定义的。单个数据点，由k四元组表示。所得的高维隐式函数可以相对于输入姿势有区别，因此可以通过在3维超球体的集合上使用梯度下降来将任意姿势投射到歧管上。与以前基于VAE的人姿势先验相反，将姿势空间转化为高斯分布，我们对实际的姿势歧管进行了建模，并保留了姿势之间的距离。我们证明，POSENDF在各种下游任务中的先验胜过现有的最新方法，从降级现实世界的人类MOCAP数据，从遮挡数据恢复到从图像中恢复到3D姿势重建。此外，我们证明它可以用来通过随机抽样和投影来产生更多的姿势，而不是基于VAE的方法。

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.

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.

在面孔和机构的3D生成模型中学习解除一致，可解释和结构化的潜在代表仍然是一个开放的问题。当需要对身份特征的控制时，问题特别严重。在本文中，我们提出了一种直观但有效的自我监督方法来训练3D形变形自动化器（VAE），鼓励身份特征的解开潜在表示。通过在不同形状上交换任意特征来造成迷你批处理允许定义利用潜在表示中已知差异和相似性的损耗功能。在3D网眼上进行的实验结果表明，最先进的潜在解剖学方法无法解散面部和身体的身份特征。我们所提出的方法适当地解耦了这些特征的产生，同时保持了良好的表示和重建能力。

最近在随机运动预测中的进展，即预测单一过去的姿势序列的多个可能的未来人类动作，导致产生真正不同的未来动作，甚至可以控制一些身体部位的运动。然而，为了实现这一点，最先进的方法需要学习用于多样性的多个映射和用于可控运动预测的专用模型。在本文中，我们向统一的深度生成网络介绍了多种和可控的运动预测。为此，我们利用了现实人类动作的直觉由有效姿势的平滑序列组成，并且给定的有限数据，学习姿势比动作更具易行。因此，我们设计了一种发电机，其顺序地预测不同车身部件的运动，并引入基于流动的基于流动的姿势，以及接合角度损失，以实现运动现实主义。在两个标准基准数据集，人类3.6m和人文集上进行实验。我展示了我们的方法在样本多样性和准确性方面优于最先进的基线。该代码可在https://github.com/wei-mao-2019/gsps获得

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。

我们提出了一种基于优化的新型范式，用于在图像和扫描上拟合3D人类模型。与直接回归输入图像中低维统计体模型（例如SMPL）的参数的现有方法相反，我们训练了每个vertex神经场网络的集合。该网络以分布式的方式预测基于当前顶点投影处提取的神经特征的顶点下降方向。在推断时，我们在梯度降低的优化管道中采用该网络，称为LVD，直到其收敛性为止，即使将所有顶点初始化为单个点，通常也会以一秒钟的分数出现。一项详尽的评估表明，我们的方法能够捕获具有截然不同的身体形状的穿着的人体，与最先进的人相比取得了重大改进。 LVD也适用于人类和手的3D模型配合，为此，我们以更简单，更快的方法对SOTA显示出显着改善。

我们的目标是从规定的行动类别中解决从规定的行动类别创造多元化和自然人动作视频的有趣但具有挑战性的问题。关键问题在于能够在视觉外观中综合多种不同的运动序列。在本文中通过两步过程实现，该两步处理维持内部3D姿势和形状表示，Action2Motion和Motion2Video。 Action2Motion随机生成规定的动作类别的合理的3D姿势序列，该类别由Motion2Video进行处理和呈现，以形成2D视频。具体而言，Lie代数理论从事人类运动学的物理法之后代表自然人动作;开发了一种促进输出运动的分集的时间变化自动编码器（VAE）。此外，给定衣服人物的额外输入图像，提出了整个管道以提取他/她的3D详细形状，并在视频中呈现来自不同视图的合理运动。这是通过改进从单个2D图像中提取3D人类形状和纹理，索引，动画和渲染的现有方法来实现这一点，以形成人类运动的2D视频。它还需要3D人类运动数据集的策策和成果进行培训目的。彻底的经验实验，包括消融研究，定性和定量评估表现出我们的方法的适用性，并展示了解决相关任务的竞争力，其中我们的方法的组成部分与最先进的方式比较。

人类将他们的手和身体一起移动，沟通和解决任务。捕获和复制此类协调活动对于虚拟字符至关重要，以实际行为行为。令人惊讶的是，大多数方法分别对待身体和手的3D建模和跟踪。在这里，我们制定了一种手和身体的型号，并将其与全身4D序列合理。当扫描或捕获3D中的全身时，手很小，通常是部分闭塞，使其形状和难以恢复。为了应对低分辨率，闭塞和噪音，我们开发了一种名为Mano（具有铰接和非刚性变形的手模型）的新型号。曼诺从大约1000个高分辨率的3D扫描中学到了31个受试者的手中的大约一定的手。该模型是逼真的，低维，捕获非刚性形状的姿势变化，与标准图形封装兼容，可以适合任何人类的手。 Mano提供从手姿势的紧凑型映射，以构成混合形状校正和姿势协同效应的线性歧管。我们将Mano附加到标准参数化3D体形状模型（SMPL），导致完全铰接的身体和手部模型（SMPL + H）。我们通过用4D扫描仪捕获的综合体，自然，自然，自然的受试者的活动来说明SMPL + H.该配件完全自动，并导致全身型号，自然地移动详细的手动运动和在全身性能捕获之前未见的现实主义。模型和数据在我们的网站上自由用于研究目的（http://mano.is.tue.mpg.de）。

仅使用单视2D照片的收藏集对3D感知生成对抗网络（GAN）的无监督学习最近取得了很多进展。然而，这些3D gan尚未证明人体，并且现有框架的产生的辐射场不是直接编辑的，从而限制了它们在下游任务中的适用性。我们通过开发一个3D GAN框架来解决这些挑战的解决方案，该框架学会在规范的姿势中生成人体或面部的辐射场，并使用显式变形场将其扭曲成所需的身体姿势或面部表达。使用我们的框架，我们展示了人体的第一个高质量的辐射现场生成结果。此外，我们表明，与未接受明确变形训练的3D GAN相比，在编辑其姿势或面部表情时，我们的变形感知训练程序可显着提高产生的身体或面部的质量。

Recent approaches to drape garments quickly over arbitrary human bodies leverage self-supervision to eliminate the need for large training sets. However, they are designed to train one network per clothing item, which severely limits their generalization abilities. In our work, we rely on self-supervision to train a single network to drape multiple garments. This is achieved by predicting a 3D deformation field conditioned on the latent codes of a generative network, which models garments as unsigned distance fields. Our pipeline can generate and drape previously unseen garments of any topology, whose shape can be edited by manipulating their latent codes. Being fully differentiable, our formulation makes it possible to recover accurate 3D models of garments from partial observations -- images or 3D scans -- via gradient descent. Our code will be made publicly available.

We describe the first method to automatically estimate the 3D pose of the human body as well as its 3D shape from a single unconstrained image. We estimate a full 3D mesh and show that 2D joints alone carry a surprising amount of information about body shape. The problem is challenging because of the complexity of the human body, articulation, occlusion, clothing, lighting, and the inherent ambiguity in inferring 3D from 2D. To solve this, we first use a recently published CNN-based method, DeepCut, to predict (bottom-up) the 2D body joint locations. We then fit (top-down) a recently published statistical body shape model, called SMPL, to the 2D joints. We do so by minimizing an objective function that penalizes the error between the projected 3D model joints and detected 2D joints. Because SMPL captures correlations in human shape across the population, we are able to robustly fit it to very little data. We further leverage the 3D model to prevent solutions that cause interpenetration. We evaluate our method, SMPLify, on the Leeds Sports, HumanEva, and Human3.6M datasets, showing superior pose accuracy with respect to the state of the art.

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

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.

为了使3D人的头像广泛可用，我们必须能够在任意姿势中产生各种具有不同身份和形状的多种3D虚拟人。由于衣服的身体形状，复杂的关节和由此产生的丰富，随机几何细节，这项任务是挑战的挑战。因此，目前代表3D人的方法不提供服装中的人的全部生成模型。在本文中，我们提出了一种新的方法，这些方法可以学习在具有相应的剥皮重量的各种衣服中产生详细的3D形状。具体而言，我们设计了一个多主题前进的剥皮模块，这些模块只有几个受试者的未预装扫描。为了捕获服装中高频细节的随机性，我们利用对抗的侵害制定，鼓励模型捕获潜在统计数据。我们提供了经验证据，这导致了皱纹的局部细节的现实生成。我们表明我们的模型能够产生佩戴各种和详细的衣服的自然人头像。此外，我们表明我们的方法可以用于拟合人类模型到原始扫描的任务，优于以前的最先进。

and ACCAD [5] datasets. The input is sparse markers and the output is SMPL body models.

建筑环境中许多物体的形状由他们与人体的关系决定：一个人将如何与这个对象进行互动？ 3D形状的现有数据驱动的生成模型产生合理的物体，但不会理由对人体的那些物体的关系。在本文中，我们学习了3D形状的身体感知生成模型。具体而言，我们培养椅子的生成型号，一种无处不在的形状类别，可以在给定的身体形状或坐姿姿势调节。身体形状调节的型号生产椅子，为具有给定体形的人舒适;姿势调节模型生产适应坐姿的椅子。要训​​练这些模型，我们定义了“坐姿匹配”度量标准和小说“坐姿舒适”度量。计算这些指标需要昂贵的优化将身体置于椅子上，这太慢被用作用于训练生成模型的损耗功能。因此，我们训练神经网络以有效地近似这些度量。我们使用我们的方法培训三个身体感知生成形状模型：基于结构的零件的发电机，点云发生器和隐式表面发生器。在所有情况下，我们的方法都生产适应其输出椅形状以输入人体规格的型号。

Three-dimensional geometric data offer an excellent domain for studying representation learning and generative modeling. In this paper, we look at geometric data represented as point clouds. We introduce a deep AutoEncoder (AE) network with state-of-the-art reconstruction quality and generalization ability. The learned representations outperform existing methods on 3D recognition tasks and enable shape editing via simple algebraic manipulations, such as semantic part editing, shape analogies and shape interpolation, as well as shape completion. We perform a thorough study of different generative models including GANs operating on the raw point clouds, significantly improved GANs trained in the fixed latent space of our AEs, and Gaussian Mixture Models (GMMs). To quantitatively evaluate generative models we introduce measures of sample fidelity and diversity based on matchings between sets of point clouds. Interestingly, our evaluation of generalization, fidelity and diversity reveals that GMMs trained in the latent space of our AEs yield the best results overall.