I am a fourth-year Ph.D. student in Computer Science at National Yang Ming Chiao Tung University (NYCU) , advised by Prof. Yu-Lun Liu at the Computational Photography Lab. My research focuses on generative 3D vision, with a particular interest in procedural and programmatic 3D representations for controllable 3D generation and editing.
I am currently a research intern at Alaya Lab at Shanda AI Research Tokyo , working on procedural 3D generation with Zhixiang Wang .
InfiniDream turns a single text prompt into a photorealistic, open-ended 3D world: a VLM plans the scene and precisely edits sophisticated procedural code, so every asset stays high-quality and a new seed grows a new world.
GaMO reformulates sparse-view 3D reconstruction as multi-view outpainting, expanding the field of view with geometry-aware diffusion to achieve consistent, high-quality reconstructions efficiently from very few input views.
Voxify3D is a differentiable two-stage method that converts 3D meshes into stylized voxel art with discrete palette control. It preserves semantic structure using multi-view pixel-art supervision and CLIP-guided optimization.
Splannequin freezes dynamic Gaussian splats into crisp 3D scenes from monocular videos by anchoring artifacts to more reliable temporal states.
Introduces depth-aware unseen mask generation, Adaptive Guided Depth Diffusion (zero-shot), and SDEdit-based detail enhancement for multi-view coherence.
Converted natural images into layered SVGs for intuitive and editable graphics. Achieved structure-preserving vectorization for AI-assisted design and editing.
Email: yichuanh.cs12@nycu.edu.tw