Reflection Separation from a Single Image via Joint Latent Diffusion
About
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/
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Reflection layer separation | SIR2 | PSNR21.14 | 10 | |
| Transmission Layer Separation | Real20 | PSNR25.32 | 8 | |
| Transmission Layer Separation | Nature | PSNR26.71 | 8 | |
| Transmission Layer Separation | Real 20 (test) | PSNR25.32 | 8 | |
| Transmission Layer Separation | Nature 20 (test) | PSNR26.71 | 8 | |
| Transmission Layer Separation | SIR2 | PSNR25.35 | 8 | |
| Transmission Layer Separation | SIR2 454 (test) | PSNR25.35 | 8 |