4 papers
TaoTex: Boosting Texture Detail Fidelity for Native 3D Material Generation
Xiuchao Wu, Shuichang Lai, Jiangjing Lyu +1
Recent 3D generation models can produce accurate geometries while still struggling to reconstruct detailed textures. We propose a diffusion-based native 3D material generation mode…
FILIGREE3D: Scaling Sparse Latent Flow Matching for Ultra-High-Resolution Image-to-3D Generation
Hongjie Li, Xinran Yang, Xiuchao Wu +2
Scaling image-to-3D generation to ultra-high resolutions requires controlling rapidly growing computational costs without sacrificing fine geometric detail. We present \textbf{Fili…
MatMart: Material Reconstruction of 3D Objects via Diffusion
Xiuchao Wu, Pengfei Zhu, Jiangjing Lyu +5
Applying diffusion models to physically-based material estimation and generation has recently gained prominence. In this paper, we propose \ttt, a novel material reconstruction fra…
StableIntrinsic: Detail-preserving One-step Diffusion Model for Multi-view Material Estimation
Xiuchao Wu, Pengfei Zhu, Jiangjing Lyu +5
Recovering material information from images has been extensively studied in computer graphics and vision. Recent works in material estimation leverage diffusion model showing promi…