Single-image reflection removal via self-supervised diffusion models

Reflections often degrade the visual quality of images captured through transparent surfaces, and reflection removal methods suffer from the shortage of paired real-world samples. This paper proposes a hybrid approach that combines cycle consistency with denoising diffusion probabilistic models (DDPM) to effectively remove reflections from single images without requiring paired training data. The method introduces a reflective removal network (RRN) that leverages DDPMs to model the decomposition process and recover the transmission image, and a reflective synthesis network (RSN) that re-synthesizes the input image using the separated components through a nonlinear attention-based mechanism. Experimental results demonstrate the effectiveness of the proposed method on the SIR \(^2\) $_{}^2$ , flash-based reflection removal (FRR) dataset, and a newly introduced museum reflection removal (MRR) dataset, showing superior performance compared to state-of-the-art methods.