Flash-Splat: 3D Reflection Removal with Flash Cues and Gaussian Splats
Mingyang Xie, Haoming Cai, Sachin Shah, Yiran Xu, Brandon Y. Feng,, Jia-Bin Huang, Christopher A. Metzler

TL;DR
Flash-Splat leverages modern inverse rendering and 3D Gaussian splatting to effectively separate transmitted and reflected light in scenes, simplifying data collection and outperforming existing methods.
Contribution
We propose a novel 3D reflection separation method using flash cues and Gaussian splats that requires unpaired measurements, simplifying the process and improving accuracy.
Findings
Accurately reconstructs transmitted and reflected scenes in 3D
Outperforms existing 3D reflection separation methods
Works with unpaired measurements, reducing data collection complexity
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/.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsIndustrial Vision Systems and Defect Detection · Computer Graphics and Visualization Techniques · Optical Coherence Tomography Applications
