DIRECT (Decomposed Injection for Reference Composition and Target-integration) is a framework that enables pose-controllable object insertion. It integrates interactive pose manipulation with high-fidelity 2D image synthesis by decomposing insertion conditions into three visual proxies:
Appearance guidance: Captures visual details from the reference object image.
Geometry guidance: Derived from a user-adjusted 3D proxy rendered from a reconstructed 3D object.
Context guidance: From the target background scene.
By injecting these through separate pathways, DIRECT preserves reference appearance, follows user-specified poses, and adapts the object naturally to the target scene.
Usage
Please refer to the official GitHub repository for installation instructions. You can run the interactive demo with the following command:
1@inproceedings{gong2026direct,
2 title = {Direct 3D-Aware Object Insertion via Decomposed Visual Proxies},
3 author = {Jingbo Gong and Yikai Wang and Yushi Lan and Yuhao Wan and Ziheng Ouyang and Rui Zhao and Ming-Ming Cheng and Qibin Hou and Chen Change Loy},
4 booktitle = {ICML},
5 year = {2026}
6}
