CAST3D: Customizing Arbitrary 2D Assets into 3D World
Jun 24, 2026·
·
1 min read
Hao Qin
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
Accepted by ECCV 2026. The PDF will be updated to the camera-ready version after release.
Authors
Ph.D. Student in Artificial Intelligence
I am a Ph.D. student in the College of Computer Science and Technology at
Zhejiang University. My research focuses on 3D vision, 3D Gaussian Splatting,
3D-AIGC, and multi-agent systems, with broader interests in self-supervised
representation learning and embodied visual content creation.