In this paper, we introduce MeshMamba, a neural network model for learning 3D articulated mesh models by employing the recently proposed Mamba State Space Models (Mamba-SSMs). MeshMamba is efficient and scalable in handling a large number of input tokens, enabling the generation and reconstruction of body mesh models with more than 10,000 vertices, capturing clothing and hand geometries. The key to effectively learning MeshMamba is the serialization technique of mesh vertices into orderings that are easily processed by Mamba. This is achieved by sorting the vertices based on body part annotations or the 3D vertex locations of a template mesh, such that the ordering respects the structure of articulated shapes. Based on MeshMamba, we design 1) MambaDiff3D, a denoising diffusion model for generating 3D articulated meshes and 2) Mamba-HMR, a 3D human mesh recovery model that reconstructs a human body shape and pose from a single image. Experimental results showed that MambaDiff3D can generate dense 3D human meshes in clothes, with grasping hands, etc., and outperforms previous approaches in the 3D human shape generation task. Additionally, Mamba-HMR extends the capabilities of previous non-parametric human mesh recovery approaches, which were limited to handling body-only poses using around 500 vertex tokens, to the whole-body setting with face and hands, while achieving competitive performance in (near) real-time.
Georgia Tech（佐治亚理工学院）；University of Bonn（波恩大学）；Facebook Reality Labs（Facebook现实实验室）；Epic Games（Epic Games公司）
The combination of traditional rendering with neural networks in Deferred Neural Rendering (DNR) provides a compelling balance between computational complexity and realism of the resulting images. Using skinned meshes for rendering articulating objects is a natural extension for the DNR framework and would open it up to a plethora of applications. However, in this case the neural shading step must account for deformations that are possibly not captured in the mesh, as well as alignment inaccuracies and dynamics -- which can confound the DNR pipeline. We present Articulated Neural Rendering (AN…
University of British Columbia（不列颠哥伦比亚大学）；Reality Labs Research（现实实验室研究部门）
Deep learning greatly improved the realism of animatable human models by learning geometry and appearance from collections of 3D scans, template meshes, and multi-view imagery. High-resolution models enable photo-realistic avatars but at the cost of requiring studio settings not available to end users. Our goal is to create avatars directly from raw images without relying on expensive studio setups and surface tracking. While a few such approaches exist, those have limited generalization capabilities and are prone to learning spurious (chance) correlations between irrelevant body parts, result…
Sichuan University（四川大学）；Chengdu Technological University（成都工业学院）；University of California-San Diego（加州大学圣地亚哥分校）
This letter presents a novel approach to extract reliable dense and long-range motion trajectories of articulated human in a video sequence. Compared with existing approaches that emphasize temporal consistency of each tracked point, we also consider the spatial structure of tracked points on the articulated human. We treat points as a set of vertices, and build a triangle mesh to join them in image space. The problem of extracting long-range motion trajectories is changed to the issue of consistency of mesh evolution over time. First, self-occlusion is detected by a novel mesh-based method an…
Estimating 3D hand meshes from single RGB images is challenging, due to intrinsic 2D-3D mapping ambiguities and limited training data. We adopt a compact parametric 3D hand model that represents deformable and articulated hand meshes. To achieve the model fitting to RGB images, we investigate and contribute in three ways: 1) Neural rendering: inspired by recent work on human body, our hand mesh estimator (HME) is implemented by a neural network and a differentiable renderer, supervised by 2D segmentation masks and 3D skeletons. HME demonstrates good performance for estimating diverse hand shap…
Few-Shot Physically-Aware Articulated Mesh Generation via Hierarchical Deformation
Tsinghua University（清华大学）；Shanghai Qi Zhi Institute（上海期智研究院）；Beijing Institute for General Artificial Intelligence（北京通用人工智能研究院）；Peking University（北京大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）
University of Bonn（波恩大学）；MPI for Intelligent Systems（马克斯·普朗克智能系统研究所）
Although commercial and open-source software exist to reconstruct a static object from a sequence recorded with an RGB-D sensor, there is a lack of tools that build rigged models of articulated objects that deform realistically and can be used for tracking or animation. In this work, we fill this gap and propose a method that creates a fully rigged model of an articulated object from depth data of a single sensor. To this end, we combine deformable mesh tracking, motion segmentation based on spectral clustering and skeletonization based on mean curvature flow. The fully rigged model then consi…
We present LBS-AE; a self-supervised autoencoding algorithm for fitting articulated mesh models to point clouds. As input, we take a sequence of point clouds to be registered as well as an artist-rigged mesh, i.e. a template mesh equipped with a linear-blend skinning (LBS) deformation space parameterized by a skeleton hierarchy. As output, we learn an LBS-based autoencoder that produces registered meshes from the input point clouds. To bridge the gap between the artist-defined geometry and the captured point clouds, our autoencoder models pose-dependent deviations from the template geometry. D…
Google Research（谷歌研究院）；MPI for Informatics（马克斯·普朗克信息学研究所）；University of Toronto（多伦多大学）
Efficient representation of articulated objects such as human bodies is an important problem in computer vision and graphics. To efficiently simulate deformation, existing approaches represent 3D objects using polygonal meshes and deform them using skinning techniques. This paper introduces neural articulated shape approximation (NASA), an alternative framework that enables efficient representation of articulated deformable objects using neural indicator functions that are conditioned on pose. Occupancy testing using NASA is straightforward, circumventing the complexity of meshes and the issue…
Human-object interactions with articulated objects are common in everyday life. Despite much progress in single-view 3D reconstruction, it is still challenging to infer an articulated 3D object model from an RGB video showing a person manipulating the object. We canonicalize the task of articulated 3D human-object interaction reconstruction from RGB video, and carry out a systematic benchmark of five families of methods for this task: 3D plane estimation, 3D cuboid estimation, CAD model fitting, implicit field fitting, and free-form mesh fitting. Our experiments show that all methods struggle …
We present imGHUM, the first holistic generative model of 3D human shape and articulated pose, represented as a signed distance function. In contrast to prior work, we model the full human body implicitly as a function zero-level-set and without the use of an explicit template mesh. We propose a novel network architecture and a learning paradigm, which make it possible to learn a detailed implicit generative model of human pose, shape, and semantics, on par with state-of-the-art mesh-based models. Our model features desired detail for human models, such as articulated pose including hand motio…
University College London（伦敦大学学院）；Snap Inc.（Snap 公司）
Monocular 3D reconstruction of articulated object categories is challenging due to the lack of training data and the inherent ill-posedness of the problem. In this work we use video self-supervision, forcing the consistency of consecutive 3D reconstructions by a motion-based cycle loss. This largely improves both optimization-based and learning-based 3D mesh reconstruction. We further introduce an interpretable model of 3D template deformations that controls a 3D surface through the displacement of a small number of local, learnable handles. We formulate this operation as a structured layer re…
The last several years have seen significant progress in using depth cameras for tracking articulated objects such as human bodies, hands, and robotic manipulators. Most approaches focus on tracking skeletal parameters of a fixed shape model, which makes them insufficient for applications that require accurate estimates of deformable object surfaces. To overcome this limitation, we present a 3D model-based tracking system for articulated deformable objects. Our system is able to track human body pose and high resolution surface contours in real time using a commodity depth sensor and GPU hardw…
ETH Zürich（苏黎世联邦理工学院）；Reality Labs Research（现实实验室研究部）
We present a novel neural implicit representation for articulated human bodies. Compared to explicit template meshes, neural implicit body representations provide an efficient mechanism for modeling interactions with the environment, which is essential for human motion reconstruction and synthesis in 3D scenes. However, existing neural implicit bodies suffer from either poor generalization on highly articulated poses or slow inference time. In this work, we observe that prior knowledge about the human body's shape and kinematic structure can be leveraged to improve generalization and efficienc…
We tackle the problem of monocular 3D reconstruction of articulated objects like humans and animals. We contribute DensePose 3D, a method that can learn such reconstructions in a weakly supervised fashion from 2D image annotations only. This is in stark contrast with previous deformable reconstruction methods that use parametric models such as SMPL pre-trained on a large dataset of 3D object scans. Because it does not require 3D scans, DensePose 3D can be used for learning a wide range of articulated categories such as different animal species. The method learns, in an end-to-end fashion, a so…
Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）
The SMPL body model is widely used for the estimation, synthesis, and analysis of 3D human pose and shape. While popular, we show that SMPL has several limitations and introduce STAR, which is quantitatively and qualitatively superior to SMPL. First, SMPL has a huge number of parameters resulting from its use of global blend shapes. These dense pose-corrective offsets relate every vertex on the mesh to all the joints in the kinematic tree, capturing spurious long-range correlations. To address this, we define per-joint pose correctives and learn the subset of mesh vertices that are influenced …
Infinite Mobility: Scalable High-Fidelity Synthesis of Articulated Objects via Procedural Generation
Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；South China University of Technology（华南理工大学）；University of Science and Technology of China（中国科学技术大学）；Tongji University（同济大学）；Fudan University（复旦大学）；Harbin Institute of Technology（哈尔滨工业大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；The University of Hong Kong（香港大学）
ETH Zürich（苏黎世联邦理工学院）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；NVIDIA（英伟达）；University of Tübingen（图宾根大学）
Neural fields have revolutionized the area of 3D reconstruction and novel view synthesis of rigid scenes. A key challenge in making such methods applicable to articulated objects, such as the human body, is to model the deformation of 3D locations between the rest pose (a canonical space) and the deformed space. We propose a new articulation module for neural fields, Fast-SNARF, which finds accurate correspondences between canonical space and posed space via iterative root finding. Fast-SNARF is a drop-in replacement in functionality to our previous work, SNARF, while significantly improving i…
Biology Laboratory, Technische Universit\" a t Berlin, Germany. denotes equal contribution.
We present a dataset with models of 14 articulated objects commonly found in human environments and with RGB-D video sequences and wrenches recorded of human interactions with them. The 358 interaction sequences total 67 minutes of human manipulation under varying experimental conditions (type of interaction, lighting, perspective, and background). Each interaction with an object is annotated with the ground truth poses of its rigid parts and the kinematic state obtained by a motion capture system. For a subset of 78 sequences (25 minutes), we also measured the interaction wrenches. The object…
Imperial College London（帝国理工学院）；Università della Svizzera italiana（瑞士意大利语区大学）；Ariel AI（Ariel人工智能公司）；Twitter, Inc.（推特公司）
Monocular 3D reconstruction of deformable objects, such as human body parts, has been typically approached by predicting parameters of heavyweight linear models. In this paper, we demonstrate an alternative solution that is based on the idea of encoding images into a latent non-linear representation of meshes. The prior on 3D hand shapes is learned by training an autoencoder with intrinsic graph convolutions performed in the spectral domain. The pre-trained decoder acts as a non-linear statistical deformable model. The latent parameters that reconstruct the shape and articulated pose of hands …
REArtGS: Reconstructing and Generating Articulated Objects via 3D Gaussian Splatting with Geometric and Motion Constraints
Hefei Institutes of Physical Science Chinese Academy of Sciences（合肥物理研究所中国科学院）；University of Science and Technology of China（中国科学技术大学）；Hefei University of Technology（合肥工业大学）；Shanghai Jiao Tong University（上海交通大学）；ByteDance（字节跳动）
ETH Zürich（苏黎世联邦理工学院）；KU Leuven（鲁汶大学）；National University of Singapore（新加坡国立大学）
We present a method for recovering the dense 3D surface of the hand by regressing the vertex coordinates of a mesh model from a single depth map. To this end, we use a two-stage 2D fully convolutional network architecture. In the first stage, the network estimates a dense correspondence field for every pixel on the depth map or image grid to the mesh grid. In the second stage, we design a differentiable operator to map features learned from the previous stage and regress a 3D coordinate map on the mesh grid. Finally, we sample from the mesh grid to recover the mesh vertices, and fit it an arti…
We present AROS, a one-shot learning approach that uses an explicit representation of interactions between highly-articulated human poses and 3D scenes. The approach is one-shot as the method does not require re-training to add new affordance instances. Furthermore, only one or a small handful of examples of the target pose are needed to describe the interaction. Given a 3D mesh of a previously unseen scene, we can predict affordance locations that support the interactions and generate corresponding articulated 3D human bodies around them. We evaluate on three public datasets of scans of real …
NVIDIA（英伟达）；Georgia Institute of Technology（佐治亚理工学院）；NVIDIA Research（英伟达研究院）
Acquisition and creation of digital human avatars is an important problem with applications to virtual telepresence, gaming, and human modeling. Most contemporary approaches for avatar generation can be viewed either as 3D-based methods, which use multi-view data to learn a 3D representation with appearance (such as a mesh, implicit surface, or volume), or 2D-based methods which learn photo-realistic renderings of avatars but lack accurate 3D representations. In this work, we present, DRaCoN, a framework for learning full-body volumetric avatars which exploits the advantages of both the 2D and…
University of Luxembourg（卢森堡大学）；Artec3D（Artec3D公司）
We propose 3DBooSTeR, a novel method to recover a textured 3D body mesh from a textured partial 3D scan. With the advent of virtual and augmented reality, there is a demand for creating realistic and high-fidelity digital 3D human representations. However, 3D scanning systems can only capture the 3D human body shape up to some level of defects due to its complexity, including occlusion between body parts, varying levels of details, shape deformations and the articulated skeleton. Textured 3D mesh completion is thus important to enhance 3D acquisitions. The proposed approach decouples the shape…
SkelGen4D: Weakly-Supervised Skeleton-Based 4D Generation for Text-Driven Mesh Animation
School of Data Science, Lingnan University（岭南大学数据科学学院）；Department of Computer Science and Engineering, Chinese University of Hong Kong（香港中文大学计算机科学与工程系）；Autodesk Research（Autodesk研究院）；Institute of Computer Applications, Shanghai Jiao Tong University（上海交通大学计算机应用研究所）
Articulated hand pose and shape estimation is an important problem for vision-based applications such as augmented reality and animation. In contrast to the existing methods which optimize only for joint positions, we propose a fully supervised deep network which learns to jointly estimate a full 3D hand mesh representation and pose from a single depth image. To this end, a CNN architecture is employed to estimate parametric representations i.e. hand pose, bone scales and complex shape parameters. Then, a novel hand pose and shape layer, embedded inside our deep framework, produces 3D joint po…
Shanghai Jiao Tong University（上海交通大学）；Simon Fraser University（西蒙弗雷泽大学）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）
Hand, the bearer of human productivity and intelligence, is receiving much attention due to the recent fever of digital twins. Among different hand morphable models, MANO has been widely used in vision and graphics community. However, MANO disregards textures and accessories, which largely limits its power to synthesize photorealistic hand data. In this paper, we extend MANO with Diverse Accessories and Rich Textures, namely DART. DART is composed of 50 daily 3D accessories which varies in appearance and shape, and 325 hand-crafted 2D texture maps covers different kinds of blemishes or make-up…
Neural-ABC: Neural Parametric Models for Articulated Body with Clothes
School of Data Science, University of Science and Technology of China（中国科学技术大学数据科学学院）；School of Mathematical Science, University of Science and Technology of China（中国科学技术大学数学科学学院）
