ArtCrafter is a feed‑forward generative model that creates articulated 3D objects from two images—one in the rest state and one in the open state. It uses a DiT‑based architecture with a $1+2N$ slot layout inspired by Slot Attention to jointly produce part‑level meshes for both states, while Triplet Attention and a repulsion loss enforce geometric consistency and prevent part penetration. The model analytically derives URDF joint parameters from the paired meshes, offering an interpretable alternative to learned regression, and outperforms existing methods in geometry quality and articulation precision on both in‑distribution and out‑of‑distribution datasets.
Artic-O is an end‑to‑end, feed‑forward framework that reconstructs articulated objects from sparse images by learning latent geometry. It maps multi‑state observations into a pretrained latent geometry space, uses a frozen flow‑matching decoder for complete‑shape priors, and fuses visual tokens with geometry latents in an image‑grounded part‑reasoning module to segment active parts and predict articulation. Trained with a geometry‑to‑articulation curriculum and a decoupled two‑pass strategy, Artic‑O achieves high reconstruction quality and articulation accuracy while drastically reducing inference time from 9 minutes to about 0.3 seconds per object.
By Xuyang Wang, Zhenyu Li, Jian Ding, Habib Slim, Peter Wonka, Hongdong Li, Mohamed Elhoseiny
MoRE introduces a Motion-Regularized Encoding for generating articulated 3D objects from a single image. It encodes joint attributes as coordinate‑aligned joint lines with axis classification and Plücker moment coefficients, and couples attribute reconstruction to motion through a differentiable expectation over joint types and axis directions. Experiments on PartNet‑Mobility and ACD demonstrate improved part‑box agreement, articulated‑state geometry, visual similarity, and reduced joint prediction errors compared to prior methods.
By Guantian Zheng, Shan Jin
FunArt is a framework that builds articulation‑aware functional 3D scene graphs from a single static RGB‑D observation. It reconstructs object instances, converts their geometry into the O‑Voxel representation of TRELLIS.2, and uses a frozen sparse‑compression VAE as a structural prior. A lightweight query‑based decoder jointly segments movable parts and functional interactive elements while estimating motion type, axis, origin, and range, achieving state‑of‑the‑art results on the Articulate3D dataset.
By Dennis Rotondi, Abdelrhman Werby, Kai O. Arras
FAMOS is a feed‑forward model that predicts movable‑part segmentation and joint parameters from a sparse, unordered set of partial point clouds. It jointly reasons over multiple observations using a Multi‑state Articulation Transformer that alternates state‑wise and global attention, and introduces an observed articulation span objective to supervise motion ranges across inputs. A procedural data generator supplies self‑annotated assets for training, and experiments on PartNet‑Mobility, ACD, and ArtiCraft‑10K show consistent improvements over existing feed‑forward and optimization‑based baselines.
By Kevin Qu, Tao Sun, Massimiliano Viola, Liyuan Zhu, Zhizhuo Zhou, Sayan Deb Sarkar, Konrad Schindler, Iro Armeni
The key challenge in articulated 3D object generation from a single image is accurately predicting the underlying kinematic structure. Existing methods either infer kinematic parameters directly from a static image that lacks dynamic part-level kinematic relationships, or estimate parameters from visual dynamics generated from a single image, which is prone to accumulated errors of two steps.
arXiv:2606. 18861v1 Announce Type: cross Abstract: Reconstructing simulation-ready digital twins of articulated objects from sensor observations remains constrained by two persistent gaps: (i) part-level geometric reconstruction is decoupled from kinematic-parameter estimation, and (ii) the recovered models often violate basic dynamic invariants such as energy conservation, leading to drift when the URDF is replayed in physics simulators.
By Xinze Zhang
arXiv:2604.28130v4 Announce Type: replace
Abstract: Recent methods for arbitrary-skeleton motion capture from monocular video follow a factorized pipeline, where a Video-to-Pose network predicts join...
By Kehong Gong, Zhengyu Wen, Dao Thien Phong, Mingxi Xu, Weixia He, Qi Wang, Ning Zhang, Zhengyu Li, Guanli Hou, Dongze Lian, Xiaoyu He, Mingyuan Zhang, Hanwang Zhang
arXiv:2609.19119v1 Announce Type: new
Abstract: Human videos contain rich causal evidence for robot manipulation: they reveal how hand motion induces object motion and produces task-relevant changes...
By Jiaming Zhang, Homanga Bharadhwaj
The paper surveys 3D generation techniques tailored for embodied AI and robotics, emphasizing that beyond visual realism, generated content must include kinematic structure, material properties, and interaction capabilities. It categorizes the literature into three roles: Data Generator, Simulation Environments, and Sim2Real Bridge, each addressing different needs in training and deployment. The survey highlights a shift toward interaction readiness and identifies key bottlenecks such as limited physical annotations, quality gaps, fragmented evaluation, and the sim‑to‑real divide.
By Tianwei Ye, Yifan Mao, Minwen Liao, Jian Liu, Chunchao Guo, Dazhao Du, Quanxin Shou, Fangqi Zhu, Song Guo
arXiv:2609.27675v2 Announce Type: replace
Abstract: Understanding articulated objects is fundamental for robotic interaction, requiring accurate rigid-part discovery and the recovery of their kinemat...
By Xiaotong Li, Yixiong Jing, Junsheng Ding, Weihang Li, Benjamin Busam, Guangming Wang, Brian Sheil
arXiv:2607. 05568v1 Announce Type: cross Abstract: Representing 3D shapes as compact sets of geometric primitives is fundamental to robotics, simulation, and scene understanding.
By Gregor Kobsik, Tim Elsner, Leif Kobbelt