SF3D: Stable Fast 3D Mesh Reconstruction with UV-Unwrapping and Illumination Disentanglement

Mark Boss, Zixuan Huang, Aaryaman Vasishta, Varun Jampani

CVPR 2025 pp. 16240-16250

doi:10.1109/CVPR52734.2025.01514 /cvpr/2025/boss2025cvpr-sf3d/

Abstract

We present SF3D, a novel method for rapid and high-quality textured object mesh reconstruction from a single image in just 0.5 seconds. Unlike most existing approaches, SF3D is explicitly trained for mesh generation, incorporating a fast UV unwrapping technique that enables swift texture generation rather than relying on vertex colors. The method also learns to predict material parameters and normal maps to enhance the visual quality of the reconstructed 3D meshes. Furthermore, SF3D integrates a delighting step to effectively remove low-frequency illumination effects, ensuring that the reconstructed meshes can be easily used in novel illumination conditions. Experiments demonstrate the superior performance of SF3D over the existing techniques

PDF CVPR Semantic Scholar

Cite

Text

Boss et al. "SF3D: Stable Fast 3D Mesh Reconstruction with UV-Unwrapping and Illumination Disentanglement." Conference on Computer Vision and Pattern Recognition, 2025. doi:10.1109/CVPR52734.2025.01514

Markdown

[Boss et al. "SF3D: Stable Fast 3D Mesh Reconstruction with UV-Unwrapping and Illumination Disentanglement." Conference on Computer Vision and Pattern Recognition, 2025.](https://mlanthology.org/cvpr/2025/boss2025cvpr-sf3d/) doi:10.1109/CVPR52734.2025.01514

BibTeX

@inproceedings{boss2025cvpr-sf3d,
  title     = {{SF3D: Stable Fast 3D Mesh Reconstruction with UV-Unwrapping and Illumination Disentanglement}},
  author    = {Boss, Mark and Huang, Zixuan and Vasishta, Aaryaman and Jampani, Varun},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2025},
  pages     = {16240-16250},
  doi       = {10.1109/CVPR52734.2025.01514},
  url       = {https://mlanthology.org/cvpr/2025/boss2025cvpr-sf3d/}
}