English

Flash-Splat: 3D Reflection Removal with Flash Cues and Gaussian Splats

Computer Vision and Pattern Recognition 2024-10-04 v1 Machine Learning Image and Video Processing

Abstract

We introduce a simple yet effective approach for separating transmitted and reflected light. Our key insight is that the powerful novel view synthesis capabilities provided by modern inverse rendering methods (e.g.,~3D Gaussian splatting) allow one to perform flash/no-flash reflection separation using unpaired measurements -- this relaxation dramatically simplifies image acquisition over conventional paired flash/no-flash reflection separation methods. Through extensive real-world experiments, we demonstrate our method, Flash-Splat, accurately reconstructs both transmitted and reflected scenes in 3D. Our method outperforms existing 3D reflection separation methods, which do not leverage illumination control, by a large margin. Our project webpage is at https://flash-splat.github.io/.

Keywords

Cite

@article{arxiv.2410.02764,
  title  = {Flash-Splat: 3D Reflection Removal with Flash Cues and Gaussian Splats},
  author = {Mingyang Xie and Haoming Cai and Sachin Shah and Yiran Xu and Brandon Y. Feng and Jia-Bin Huang and Christopher A. Metzler},
  journal= {arXiv preprint arXiv:2410.02764},
  year   = {2024}
}
R2 v1 2026-06-28T19:07:28.624Z