Placing Any Object at Any 3D Position

Jan 2, 2026·
Junhao Zhang
,
Ming Kong
,
Zhanbin Hu
秦皓
秦皓
,
Zhijie Xu
,
Xiaojun Zhu
,
Qiang Zhu
· 1 min read
Abstract
This work proposes a diffusion-based method for 3D-aware image composition. Users specify an object’s 3D bounding box, and the method generates high-fidelity composites guided by image, object identity, and depth constraints.
Type
Publication
AAAI Conference on Artificial Intelligence
publications

The method supports precise 3D object placement for image composition, improving depth, occlusion, and spatial coherence over purely 2D placement pipelines.

Image Composition 3D-Aware Editing Diffusion Models
秦皓
Authors
秦皓
Ph.D. Student at Zhejiang University

I am a Ph.D. student in the College of Computer Science and Technology at Zhejiang University. My research focuses on spatial intelligence, 3D-AIGC, multi-agent systems, latent reasoning for VLMs, and contrastive learning, with a broader interest in building intelligent systems that connect perception, reasoning, and controllable creation in the world.

Email: haoqin@zju.edu.cn