Reflection Separation from a Single Image via Joint Latent Diffusion

Researchers have developed a diffusion model that separates reflections from a single image by simultaneously generating transmission and reflection layers through a unified framework. The model introduces a cross-layer self-attention mechanism for feature disentanglement and a disjoint sampling strategy to reduce interference between layers during diffusion. The approach outperforms existing methods on real-world benchmarks, addressing challenges like glare and weak reflections where prior techniques often fail.

arXiv:2606.04107v1 Announce Type: new Abstract: Single-image reflection separation is highly challenging under extreme conditions like glare or weak reflections. Existing methods often struggle to recover both layers in glare or weak-reflection scenarios because of insufficient information. This paper presents a diffusion model explicitly fine-tuned for this task, leveraging generative diffusion priors for robust separation. Our method simultaneously generates transmission and reflection layers through a unified diffusion model, incorporating a novel cross-layer self-attention mechanism for better feature disentanglement. We further introduce a disjoint sampling strategy to iteratively reduce interference between the layers during diffusion and a latent optimization step with a learned composition function for improved results in complex real-world scenarios. Extensive experiments demonstrate that our approach surpasses state-of-the-art methods on multiple real-world benchmarks. Project page: https://brian90709.github.io/diff-reflection-separation/