FlexPart is a new framework that enables text‑controlled, semantics‑aware 3D mesh segmentation at any desired granularity. It introduces a holistic control prompt that combines part names with location and shape clauses, and uses a Vision‑Language Model pipeline to generate a large multi‑granularity dataset. The model produces a view‑independent part‑identity field in 3D space, and an inference‑time VLM planner can auto‑complete descriptive clauses from 2D renderings, allowing users to specify parts with ordinary words. FlexPart outperforms strong baselines by up to 22% in mIoU on its benchmark and improves selective segmentation by 35% over click‑driven methods.
By Yiqun Zhao, Jiachen Xu, Yihao Zhi, Yunfei Zhao, Zibo Zhao, Xintong Han, Chunchao Guo, Shenghua Gao
arXiv:2609.25832v1 Announce Type: new
Abstract: Part segmentation is a fundamental problem in computer graphics and 3D vision. Recent works have expanded 3D part segmentation beyond fixed taxonomies,...
By Zhe Zhu, Yiheng Zhang, Peng Li, Zixing Zhao, Honghua Chen, Yaqing Zhang, Le Wan, Zhiyang Dou, Cheng Lin, Yuan Liu, Mingqiang Wei, Wenping Wang
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
OmniLatent is a unified latent modeling framework that jointly encodes geometry, deformation, appearance, and binary part IDs for 3D part decomposition. By learning a shared latent space, it enables a single-pass generation of part-aware 3D assets from a single input image, eliminating the need for separate segmentation stages. The framework also supports extensions such as a point-prompt adapter for full segmentation and an amodal part completion model that reconstructs missing parts while maintaining global consistency.
By Yunhan Yang, Yunfei Zhao, Zeqiang Lai, Jiachen Xu, Minxiu Wang, Xintong Han, Xiangyu Yue, Xihui Liu, Chunchao Guo
UniRAP is a unified model that infers part-level physical affordances and translates language instructions into actionable geometric representations. It treats the task as a conditional multimodal generation problem, integrating visual inputs, textual instructions, and optional prompts into a shared spatiotemporal representation via a unified interface token mechanism. The model employs a Unified Affordance Decoder to jointly perform object detection, part-level affordance segmentation, and 4‑DoF interaction pose estimation, and uses a curriculum-based transfer training strategy to improve data efficiency with limited textual annotations.
By Linfei Li, Ruining Hu, Lin Zhang, Zhong Wang, Fengyi Zhang, Ying Shen, Binqiang Wang, Xin Zhang
Vision-language perception has achieved impressive progress in aligning natural language with visual observations, yet grounding high-level semantics into part-level physical interaction remains chall...
arXiv:2602.13444v2 Announce Type: replace-cross
Abstract: Recent vision-language-action (VLA) models can generate plausible end-effector motions, yet they often fail in long-horizon, contact-rich tas...
By Huajian Zeng, Lingyun Chen, Jiaqi Yang, Yuantai Zhang, Fan Shi, Peidong Liu, Xingxing Zuo
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:2609.36918v1 Announce Type: new
Abstract: Part-level 3D assets are essential for editing, reassembly, and interaction, yet recovering such structure from a single image remains challenging due...
By Jiantao Lin, Meixi Chen, Yingjie Xu, Chenbo Fu, Leyi Wu, Hao Chen, Yinchuan Li, Ying-Cong Chen
AffordSim is a scalable data generator and benchmark that integrates open‑vocabulary 3D affordance prediction into simulation‑based trajectory generation for robotic manipulation. Given a natural‑language task description, it synthesizes task‑relevant scenes, queries affordances, grounds them on object surfaces, samples region‑conditioned grasps, and selects executable candidates with motion planning, while randomizing pose, texture, lighting, noise, and backgrounds for sim‑to‑real transfer. The benchmark includes 50 tasks, five robot embodiments, and over 500 objects, achieving 93% of the success rate of manual contact annotations on affordance‑critical tasks and 89% on hard composite tasks, with policies trained on AffordSim transferring zero‑shot to a real Franka FR3 with 24% average success.
By Mingyang Li, Haofan Xu, Haowen Sun, Xinzhe Chen, Sihua Ren, Liqi Huang, Xinyang Sui, Chenyang Miao, Jiawei Ye, Qiongjie Cui, Xingyu Chen, Zeyang Liu, Xuguang Lan
arXiv:2608.20720v1 Announce Type: new
Abstract: Open-world 3D affordance grounding requires localizing functional object parts in 3D given free-form language queries. Existing methods typically assum...
By Junqi Wu, Kaihua Tang, Xuanwen Chen, Hongzhi Li, Jianqiang Huang, Xian-Sheng Hua
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.