Paper · arXiv 2408.00653
SF3D: Stable Fast 3D Mesh Reconstruction with UV-unwrapping and Illumination Disentanglement
Mark Boss, Zixuan Huang, Aaryaman Vasishta, Varun Jampani
SF3D quickly reconstructs high-quality textured 3D meshes from a single image by training for mesh generation with fast UV unwrapping, material parameter prediction, normal map estimation, and low-frequency illumination removal.
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. Project page: https://stable-fast-3d.github.io