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

2026-08-23

AI Summary

本文提出Object-Uni模型，通过将物体姿态作为共享几何变量，解决了物体实例空间状态的理解与可控生成问题。

Abstract

Unified models for visual understanding and generation have made rapid progress, yet they still lack the ability to understand and manipulate the spatial states of object instances. Existing models can describe objects in natural language, but they struggle to precisely represent continuous object poses and generate geometrically consistent images under target viewpoints. To mitigate this, we propose \emph{Object-Uni}, a unified model for object-centric spatial understanding and controllable generation. Specifically, we formulate object-centric spatial intelligence as a unified problem connecting pose perception, spatial reasoning, pose-conditioned generation, and object-centric novel view synthesis. We treat object pose as an explicit geometric variable shared by understanding and generation, rather than merely a prediction label or control signal. To make pose usable by multimodal large language models, we propose a viewpoint-based orientation abstraction that maps orientation into structured viewpoint descriptions while preserving continuous geometric supervision. We further construct an object-centric spatial benchmark (UniSpatial-80K) and train a unified model with an object-token-grounded pose anchor to associate each instance with its pose state. Experiments show that our model improves object-level pose understanding and pose-controllable generation, moving unified models from describing objects toward manipulating spatial states.

Problem

• visual understanding
• generation
• object instances
• spatial states
• continuous object poses

Innovation

• Unified Model
• Object-Centric
• Pose Perception
• Viewpoint-based Orientation Abstraction
• Controllable Generation