Flash-Split: 2D Reflection Removal with Flash Cues and Latent Diffusion Separation
This addresses the challenge of reflections obscuring images for computer vision applications, with incremental improvements over existing methods.
The paper tackles the problem of separating transmitted and reflected light from images with transparent surfaces using a single flash/no-flash image pair, achieving state-of-the-art performance in reflection separation.
Transparent surfaces, such as glass, create complex reflections that obscure images and challenge downstream computer vision applications. We introduce Flash-Split, a robust framework for separating transmitted and reflected light using a single (potentially misaligned) pair of flash/no-flash images. Our core idea is to perform latent-space reflection separation while leveraging the flash cues. Specifically, Flash-Split consists of two stages. Stage 1 separates apart the reflection latent and transmission latent via a dual-branch diffusion model conditioned on an encoded flash/no-flash latent pair, effectively mitigating the flash/no-flash misalignment issue. Stage 2 restores high-resolution, faithful details to the separated latents, via a cross-latent decoding process conditioned on the original images before separation. By validating Flash-Split on challenging real-world scenes, we demonstrate state-of-the-art reflection separation performance and significantly outperform the baseline methods.