← Back to all news
arXiv AI By Mining Tan, Yinuo Wang, Ziqi Zhou, Weize Quan, Sifei Li, Jingdong Chen, DanDan Zheng, Libin Wang, Weiming Dong

Object-Uni: A Unified Model for Object-Centric Spatial Understanding and Controllable Generation

Read the original on arXiv AI →

Object-Uni is a unified model that integrates pose perception, spatial reasoning, pose-conditioned generation, and novel view synthesis for object-centric spatial understanding and controllable image generation. It treats object pose as an explicit geometric variable shared across tasks and introduces a viewpoint-based orientation abstraction to make pose interpretable by multimodal large language models. The authors also create a new benchmark, UniSpatial-80K, and demonstrate that Object‑Uni improves both pose understanding and pose‑controllable generation compared to existing models.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv Computer Vision
Sep 23

Fysiverse-3D-Vision Technical Report: Generating Executable 3D Worlds from Images through Unified Spatial Reasoning

Fysiverse-3D-Vision is a unified vision‑language‑geometry framework that reconstructs executable 3D scenes from a single image. It separates spatial layout reasoning from asset synthesis, using a shared representation where spatial reasoning and geometric reconstruction reinforce each other. The model employs a Transformer that integrates textual supervision, semantic visual cues, and geometric representations, and includes an object‑conditioned layout module to predict object translation, rotation, and scale while maintaining physical consistency through collision‑aware optimization.

By Dingkang Yang, Yizhou Liu, Wendong Cheng, Zizhi Chen, Shunli Wang, Yang Liu, Hongsheng Li, Lihua Zhang
llmsroboticsmultimodalsafety
More like this →
arXiv Machine Learning
Jul 8

PoseVLA: Universal Pose Pretraining for Generalizable Vision-Language-Action Policies

arXiv:2602. 19710v3 Announce Type: replace-cross Abstract: Existing Vision-Language-Action (VLA) models often suffer from feature collapse and low training efficiency because they entangle high-level perception with sparse, embodiment-specific action supervision.

By Haitao Lin, Hanyang Yu, Jingshun Huang, He Zhang, Yonggen Ling, Ping Tan, Xiangyang Xue, Yanwei Fu
nlproboticsmultimodalbenchmarkssafety
More like this →