1. RelitLRM: Generative Relightable Radiance for Large Reconstruction Models
- Author
-
Zhang, Tianyuan, Kuang, Zhengfei, Jin, Haian, Xu, Zexiang, Bi, Sai, Tan, Hao, Zhang, He, Hu, Yiwei, Hasan, Milos, Freeman, William T., Zhang, Kai, and Luan, Fujun
- Subjects
Computer Science - Computer Vision and Pattern Recognition ,Computer Science - Graphics ,Computer Science - Machine Learning - Abstract
We propose RelitLRM, a Large Reconstruction Model (LRM) for generating high-quality Gaussian splatting representations of 3D objects under novel illuminations from sparse (4-8) posed images captured under unknown static lighting. Unlike prior inverse rendering methods requiring dense captures and slow optimization, often causing artifacts like incorrect highlights or shadow baking, RelitLRM adopts a feed-forward transformer-based model with a novel combination of a geometry reconstructor and a relightable appearance generator based on diffusion. The model is trained end-to-end on synthetic multi-view renderings of objects under varying known illuminations. This architecture design enables to effectively decompose geometry and appearance, resolve the ambiguity between material and lighting, and capture the multi-modal distribution of shadows and specularity in the relit appearance. We show our sparse-view feed-forward RelitLRM offers competitive relighting results to state-of-the-art dense-view optimization-based baselines while being significantly faster. Our project page is available at: https://relit-lrm.github.io/., Comment: webpage: https://relit-lrm.github.io/
- Published
- 2024