Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

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/

Zheng-Hui Huang, Zhixiang Wang, Yu-Lun Liu, Yung-Yu Chuang• 2026

Related benchmarks

TaskDatasetResultRank
Reflection layer separationSIR2
PSNR21.14
10
Transmission Layer SeparationReal20
PSNR25.32
8
Transmission Layer SeparationNature
PSNR26.71
8
Transmission Layer SeparationReal 20 (test)
PSNR25.32
8
Transmission Layer SeparationNature 20 (test)
PSNR26.71
8
Transmission Layer SeparationSIR2
PSNR25.35
8
Transmission Layer SeparationSIR2 454 (test)
PSNR25.35
8
Showing 7 of 7 rows

Other info

Follow for update