FUMO: Prior-Modulated Diffusion for Single Image Reflection Removal

TL;DR

FUMO introduces a diffusion-based framework with prior modulation for single image reflection removal, enhancing spatial control and structural accuracy by leveraging intensity and high-frequency priors, and employing a coarse-to-fine training strategy.

Contribution

The paper proposes a novel diffusion model with prior modulation for SIRR, utilizing explicit priors and a two-stage training process to improve reflection removal quality.

Findings

Achieves competitive quantitative results on benchmarks.

Improves perceptual quality of reflection removal.

Effectively handles challenging real-world images.

Abstract

Single image reflection removal (SIRR) is challenging in real scenes, where reflection strength varies spatially and reflection patterns are tightly entangled with transmission structures. This paper presents a diffusion model with prior modulation framework (FUMO) that introduces explicit guidance signals to improve spatial controllability and structural faithfulness. Two priors are extracted directly from the mixed image, an intensity prior that estimates spatial reflection severity and a high-frequency prior that captures detail-sensitive responses via multi-scale residual aggregation. We propose a coarse-to-fine training paradigm. In the first stage, these cues are combined to gate the conditional residual injections, focusing the conditioning on regions that are both reflection-dominant and structure-sensitive. In the second stage, a fine-grained refinement network corrects local misalignment and sharpens fine details in the image space. Experiments conducted on both standard benchmarks and challenging images in the wild demonstrate competitive quantitative results and consistently improved perceptual quality. The code is released at https://github.com/Lucious-Desmon/FUMO.