Reflection Separation from a Single Image via Joint Latent Diffusion
Quick Take
This paper introduces a novel diffusion model for single-image reflection separation, achieving superior results in glare and weak-reflection scenarios. By employing a cross-layer self-attention mechanism and a disjoint sampling strategy, the method effectively disentangles transmission and reflection layers, outperforming state-of-the-art techniques on various real-world benchmarks.
Key Points
- Introduces a diffusion model fine-tuned for reflection separation from single images.
- Utilizes a cross-layer self-attention mechanism for improved feature disentanglement.
- Implements a disjoint sampling strategy to minimize layer interference during diffusion.
- Outperforms existing methods on multiple real-world benchmarks.
- Demonstrates effectiveness in handling glare and weak-reflection conditions.
Article Excerpt
From source RSS / original summaryarXiv: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/
Reader Mode unavailable (could not extract clean content).
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CV
See more →Optimal Transport Flow Matching by Design
The study presents a novel approach to optimal transport (OT) flow matching, reformulating the problem by treating the prior as a design choice. This method achieves over 2x reduction in trajectory curvature compared to existing methods, improving generation quality in few-step regimes without altering the flow model. The approach integrates seamlessly with latent-space models and classifier-free guidance.