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 relying on mesh-laplacian regularization and show that it can be trained in an end-to-end manner. We finally introduce a per-sample numerical optimisation approach that jointly optimises over mesh displacements and cameras within a video, boosting accuracy both for training and also as test time post-processing. While relying exclusively on a small set of videos collected per category for supervision, we obtain state-of-the-art reconstructions with diverse shapes, viewpoints and textures for multiple articulated object categories.
Remarkable progress has been made in 3D reconstruction of rigid structures from a video or a collection of images. However, it is still challenging to reconstruct nonrigid structures from RGB inputs, due to its under-constrained nature. While template-based approaches, such as parametric shape models, have achieved great success in modeling the "closed world" of known object categories, they cannot well handle the "open-world" of novel object categories or outlier shapes. In this work, we introduce a template-free approach to learn 3D shapes from a single video. It adopts an analysis-by-synthe…
German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心）；Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；University of Kaiserslautern（凯泽斯劳滕大学）；University of Prince Mugrin (UPM)（穆格林王子大学）
Recovery of articulated 3D structure from 2D observations is a challenging computer vision problem with many applications. Current learning-based approaches achieve state-of-the-art accuracy on public benchmarks but are restricted to specific types of objects and motions covered by the training datasets. Model-based approaches do not rely on training data but show lower accuracy on these datasets. In this paper, we introduce a model-based method called Structure from Articulated Motion (SfAM), which can recover multiple object and motion types without training on extensive data collections. At…
FreeArtGS: Articulated Gaussian Splatting Under Free-moving Scenario
CFCS, School of Computer Science, Peking University（计算机科学系，北京大学CFCS）；College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）；PrimeBot
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…
University of British Columbia（不列颠哥伦比亚大学）；Facebook Reality Labs（Facebook现实实验室）
While deep learning reshaped the classical motion capture pipeline with feed-forward networks, generative models are required to recover fine alignment via iterative refinement. Unfortunately, the existing models are usually hand-crafted or learned in controlled conditions, only applicable to limited domains. We propose a method to learn a generative neural body model from unlabelled monocular videos by extending Neural Radiance Fields (NeRFs). We equip them with a skeleton to apply to time-varying and articulated motion. A key insight is that implicit models require the inverse of the forward…
MonoMobility: Zero-Shot 3D Mobility Analysis from Monocular Videos
National University of Defense Technology（国防科技大学）；Sun Yat-sen University（中山大学）；College of Computer and Information Science, Southwest University（西南大学计算机与信息科学学院）
DreaMo: Articulated 3D Reconstruction From A Single Casual Video
National Tsing Hua University（国立清华大学）；Carnegie Mellon University（卡内基梅隆大学）；University of California, Merced（加州大学默塞德分校）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Amazon（亚马逊）
针对单段随手拍摄互联网视频视角不全的问题，本文提出 DreaMo，结合视角条件扩散先验、定制正则化及骨架生成策略，实现高质量铰接式 3D 形状与可解释骨架重建。
Generalizable Articulated Object Perception with Superpoints
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）；China Agricultural University（中国农业大学）；National Institute of Technology, Durgapur（杜尔加尔国家理工学院）；Shanghai Jiao Tong University（上海交通大学）；National University of Singapore（新加坡国立大学）
We present StrobeNet, a method for category-level 3D reconstruction of articulating objects from one or more unposed RGB images. Reconstructing general articulating object categories % has important applications, but is challenging since objects can have wide variation in shape, articulation, appearance and topology. We address this by building on the idea of category-level articulation canonicalization -- mapping observations to a canonical articulation which enables correspondence-free multiview aggregation. Our end-to-end trainable neural network estimates feature-enriched canonical 3D poin…
National Tsing Hua University（台湾清华大学）；Massachusetts Institute of Technology（麻省理工学院）；Appier Inc.（沛星互动科技股份有限公司）
We propose CLA-NeRF -- a Category-Level Articulated Neural Radiance Field that can perform view synthesis, part segmentation, and articulated pose estimation. CLA-NeRF is trained at the object category level using no CAD models and no depth, but a set of RGB images with ground truth camera poses and part segments. During inference, it only takes a few RGB views (i.e., few-shot) of an unseen 3D object instance within the known category to infer the object part segmentation and the neural radiance field. Given an articulated pose as input, CLA-NeRF can perform articulation-aware volume rendering…
Toyota Research Institute (TRI)（丰田研究院）；University of Michigan（密歇根大学）
Self-supervised learning is showing great promise for monocular depth estimation, using geometry as the only source of supervision. Depth networks are indeed capable of learning representations that relate visual appearance to 3D properties by implicitly leveraging category-level patterns. In this work we investigate how to leverage more directly this semantic structure to guide geometric representation learning, while remaining in the self-supervised regime. Instead of using semantic labels and proxy losses in a multi-task approach, we propose a new architecture leveraging fixed pretrained se…
We study the effect of adversarial perturbations on the task of monocular depth prediction. Specifically, we explore the ability of small, imperceptible additive perturbations to selectively alter the perceived geometry of the scene. We show that such perturbations can not only globally re-scale the predicted distances from the camera, but also alter the prediction to match a different target scene. We also show that, when given semantic or instance information, perturbations can fool the network to alter the depth of specific categories or instances in the scene, and even remove them while pr…
Articulat3D: Reconstructing Articulated Digital Twins From Monocular Videos with Geometric and Motion Constraints
Wuhan University（武汉大学）；Hong Kong Embodied AI Lab（香港具身AI实验室）；The Chinese University of Hong Kong（香港中文大学）；Peking Union Medical College（北京协和医学院）；University of Macau（澳门大学）；Zhejiang University（浙江大学）
Peking University（北京大学）；Stanford University（斯坦福大学）；Shandong University（山东大学）；UCSD（加州大学圣地亚哥分校）；Tencent AI Lab（腾讯AI实验室）；Beijing Institute for General AI（北京通用人工智能研究院）
In this work, we tackle the problem of category-level online pose tracking of objects from point cloud sequences. For the first time, we propose a unified framework that can handle 9DoF pose tracking for novel rigid object instances as well as per-part pose tracking for articulated objects from known categories. Here the 9DoF pose, comprising 6D pose and 3D size, is equivalent to a 3D amodal bounding box representation with free 6D pose. Given the depth point cloud at the current frame and the estimated pose from the last frame, our novel end-to-end pipeline learns to accurately update the pos…
University College London（伦敦大学学院）；Snap Inc.（色拉布公司）
We present To The Point (TTP), a method for reconstructing 3D objects from a single image using 2D to 3D correspondences learned from weak supervision. We recover a 3D shape from a 2D image by first regressing the 2D positions corresponding to the 3D template vertices and then jointly estimating a rigid camera transform and non-rigid template deformation that optimally explain the 2D positions through the 3D shape projection. By relying on 3D-2D correspondences we use a simple per-sample optimization problem to replace CNN-based regression of camera pose and non-rigid deformation and thereby o…
Carnegie Mellon University（卡内基梅隆大学）；Apple（苹果公司）；The University of Adelaide（阿德莱德大学）
Labeling articulated objects in unconstrained settings have a wide variety of applications including entertainment, neuroscience, psychology, ethology, and many fields of medicine. Large offline labeled datasets do not exist for all but the most common articulated object categories (e.g., humans). Hand labeling these landmarks within a video sequence is a laborious task. Learned landmark detectors can help, but can be error-prone when trained from only a few examples. Multi-camera systems that train fine-grained detectors have shown significant promise in detecting such errors, allowing for se…
ArtHOI: Articulated Human-Object Interaction Synthesis by 4D Reconstruction from Video Priors
School of AIA, Huazhong University of Science and Technology（华中科技大学人工智能学院）；the S-Lab, Nanyang Technological University (NTU)（南洋理工大学S实验室）；the Beijing Academy of Artificial Intelligence (BAAI)（北京人工智能研究院）；Zhejiang University (ZJU)（浙江大学）；the Institute for AI Industry Research (AIR), Tsinghua University (THU)（清华大学人工智能产业研究院）
Self-supervised depth estimation has made a great success in learning depth from unlabeled image sequences. While the mappings between image and pixel-wise depth are well-studied in current methods, the correlation between image, depth and scene semantics, however, is less considered. This hinders the network to better understand the real geometry of the scene, since the contextual clues, contribute not only the latent representations of scene depth, but also the straight constraints for depth map. In this paper, we leverage the two benefits by proposing the implicit and explicit semantic guid…
School of Artificial Intelligence, Shanghai Jiao Tong University（上海交通大学人工智能学院）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；King Abdullah University of Science and Technology（国王 Abdullah 科学与技术大学）
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 …
We focus on the task of estimating a physically plausible articulated human motion from monocular video. Existing approaches that do not consider physics often produce temporally inconsistent output with motion artifacts, while state-of-the-art physics-based approaches have either been shown to work only in controlled laboratory conditions or consider simplified body-ground contact limited to feet. This paper explores how these shortcomings can be addressed by directly incorporating a fully-featured physics engine into the pose estimation process. Given an uncontrolled, real-world scene as inp…
