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
arXiv:2509.04276v3 Announce Type: replace
Abstract: We present a method for modeling articulated objects from sparse images with unknown camera poses. Existing approaches require dense multi-view obs...
By Jianning Deng, Kartic Subr, Hakan Bilen
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:2609.19142v1 Announce Type: new
Abstract: World models endow perceptual systems with the ability to predict how scenes evolve under interaction. They are most beneficial when trained on diverse...
By Bardienus P. Duisterhof, Kaifeng Zhang, Adam Hung, Bowen Wen, Stan Birchfield, Yunzhu Li, Deva Ramanan, Jeffrey Ichnowski
World models endow perceptual systems with the ability to predict how scenes evolve under interaction. They are most beneficial when trained on diverse volumes of data, to instill a rich prior into do...
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—by producing part‑level meshes for both states in a single forward pass. It uses a DiT‑based architecture with a $1+2N$ slot layout inspired by Slot Attention, Triplet Attention for cross‑state consistency, and a repulsion loss to avoid part penetration. The model analytically derives URDF joint parameters from the rigid transformation between paired meshes, offering an interpretable alternative to learned joint regression, and outperforms existing methods in geometry quality and articulation precision on both in‑distribution and out‑of‑distribution datasets.
By Minh Canh Tu, Quang-Binh Nguyen, Khoi Nguyen
arXiv:2609.23796v2 Announce Type: replace
Abstract: Single-image 3D object generation can now produce high-fidelity assets, yet accurately placing them into a coherent scene layout remains an open ch...
By Yang-Tian Sun, Tianjia Liu, Zehuan Huang, Yi-Hua Huang, Xiaoyang Lyu, Ziyi Yang, Zi-Xin Zou, Yuan-Chen Guo, Yan-Pei Cao, Xiaojuan Qi
arXiv:2609.23796v1 Announce Type: new
Abstract: Single-image 3D object generation can now produce high-fidelity assets, yet accurately placing them into a coherent scene layout remains an open challe...
By Yang-Tian Sun, Tianjia Liu, Zehuan Huang, Yi-Hua Huang, Xiaoyang Lyu, Ziyi Yang, Zi-Xin Zou, Yuan-Chen Guo, Yan-Pei Cao, Xiaojuan Qi
arXiv:2609.12898v1 Announce Type: new
Abstract: Fine-grained robotic manipulation depends on understanding parts, not only whole objects. Existing 3D foundation models tend to be either generalized b...
By Xinqiang Yu, Zekun qi, Jiawei He, Wenyao Zhang, Xuchuan Chen, Guaocai Yao, Li Yi, Zhaoxiang Zhang, He Wang
Accurate monocular 4D hand reconstruction remains challenging. Per-frame discriminative regressors lack temporal context and often produce jittery predictions.
The paper presents a motion- and gravity-aware framework for feed-forward transformer models in multi-view 3D reconstruction. By providing residual optical flow and gravity direction as privileged signals during training, the model learns stronger geometric representations while remaining efficient at inference. Experiments demonstrate consistent accuracy gains, particularly in dynamic scenes and challenging camera motions, with the optimal integration stage depending on the backbone architecture.
By Shiyao Qian, Yuan Ren, Dongfeng Bai
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