CAST3D: Customizing Arbitrary 2D Assets into 3D World

Jun 24, 2026·
Yukai Sun
Equal contribution
秦皓
秦皓
Equal contribution
,
Ming Kong
,
Luyuan Chen
,
Zhijie Xu
,
Jinjian Zhang
,
Jie Liu
,
Feng Zhang
,
Qiang Zhu
· 1 min read
Abstract
CAST3D is a training-free framework for transforming arbitrary 2D assets into coherent 3D objects or scenes under textual guidance. It targets controllable 3D composition and editing while preserving semantic and geometric consistency.
Type
Publication
European Conference on Computer Vision
publications

Accepted by ECCV 2026.

3D-AIGC 3D Generation Asset Customization
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