Reflection Separation from a Single Image via Joint Latent Diffusion

• URL: http://arxiv.org/abs/2606.04107v1
• Date: Tue, 02 Jun 2026 18:11:20 GMT
• Title: Reflection Separation from a Single Image via Joint Latent Diffusion
• Abstract summary: Single-image reflection separation is highly challenging under extreme conditions like glare or weak reflections.<n>This paper presents a diffusion model explicitly fine-tuned for this task, leveraging generative diffusion priors for robust separation.<n>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.
• Score: 15.007786845289223
• License: http://creativecommons.org/licenses/by/4.0/
• 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/

Related papers

• PRISM: Latent Composition Consistency for Single-Image Reflection Removal [8.368543987898734]
  Single-image reflection removal (SIRR) seeks to recover the transmission layer from a mixture corrupted by reflections.<n>Existing methods operate in pixel space, where the nonlinear sRGB formation model entangles the two layers.<n>We propose textbfPRISM (Pretrained-latent Reflection Image Separation Model), which reinterprets SIRR as a latent linear separation problem.
  arXiv  Detail & Related papers  (2026-06-30T11:28:02Z)
• Degradation-Robust Fusion: An Efficient Degradation-Aware Diffusion Framework for Multimodal Image Fusion in Arbitrary Degradation Scenarios [34.660999867031386]
  Complex degradations like noise, blur, and low resolution are typical challenges in real world image fusion tasks.<n>This paper proposes an efficient degradation aware diffusion framework for image fusion under arbitrary degradation scenarios.
  arXiv  Detail & Related papers  (2026-04-10T03:34:53Z)
• Latent Bias Alignment for High-Fidelity Diffusion Inversion in Real-World Image Reconstruction and Manipulation [25.312675775144154]
  Text-to-image diffusion models are capable of generating high-quality images guided by text prompts.<n>Can they be used to generate or approximate real-world images from the seed noise?<n> diffusion inversion problem serves as building block for bridging diffusion models and real-world scenarios.
  arXiv  Detail & Related papers  (2026-03-25T03:44:21Z)
• Dereflection Any Image with Diffusion Priors and Diversified Data [86.15504914121226]
  We propose a comprehensive solution with an efficient data preparation pipeline and a generalizable model for robust reflection removal.<n>First, we introduce a dataset named Diverse Reflection Removal (DRR) created by randomly rotating reflective mediums in target scenes.<n>Second, we propose a diffusion-based framework with one-step diffusion for deterministic outputs and fast inference.
  arXiv  Detail & Related papers  (2025-03-21T17:48:14Z)
• Oscillation Inversion: Understand the structure of Large Flow Model through the Lens of Inversion Method [60.88467353578118]
  We show that a fixed-point-inspired iterative approach to invert real-world images does not achieve convergence, instead oscillating between distinct clusters. We introduce a simple and fast distribution transfer technique that facilitates image enhancement, stroke-based recoloring, as well as visual prompt-guided image editing.
  arXiv  Detail & Related papers  (2024-11-17T17:45:37Z)
• Solving Video Inverse Problems Using Image Diffusion Models [58.464465016269614]
  We introduce an innovative video inverse solver that leverages only image diffusion models.<n>Our method treats the time dimension of a video as the batch dimension image diffusion models.<n>We also introduce a batch-consistent sampling strategy that encourages consistency across batches.
  arXiv  Detail & Related papers  (2024-09-04T09:48:27Z)
• Efficient Diffusion Model for Image Restoration by Residual Shifting [63.02725947015132]
  This study proposes a novel and efficient diffusion model for image restoration. Our method avoids the need for post-acceleration during inference, thereby avoiding the associated performance deterioration. Our method achieves superior or comparable performance to current state-of-the-art methods on three classical IR tasks.
  arXiv  Detail & Related papers  (2024-03-12T05:06:07Z)
• A Variational Perspective on Solving Inverse Problems with Diffusion Models [101.831766524264]
  Inverse tasks can be formulated as inferring a posterior distribution over data. This is however challenging in diffusion models since the nonlinear and iterative nature of the diffusion process renders the posterior intractable. We propose a variational approach that by design seeks to approximate the true posterior distribution.
  arXiv  Detail & Related papers  (2023-05-07T23:00:47Z)
• Come-Closer-Diffuse-Faster: Accelerating Conditional Diffusion Models for Inverse Problems through Stochastic Contraction [31.61199061999173]
  Diffusion models have a critical downside - they are inherently slow to sample from, needing few thousand steps of iteration to generate images from pure Gaussian noise. We show that starting from Gaussian noise is unnecessary. Instead, starting from a single forward diffusion with better initialization significantly reduces the number of sampling steps in the reverse conditional diffusion. New sampling strategy, dubbed ComeCloser-DiffuseFaster (CCDF), also reveals a new insight on how the existing feedforward neural network approaches for inverse problems can be synergistically combined with the diffusion models.
  arXiv  Detail & Related papers  (2021-12-09T04:28:41Z)
• Learning to See Through Obstructions with Layered Decomposition [117.77024641706451]
  We present a learning-based approach for removing unwanted obstructions from moving images. Our method leverages motion differences between the background and obstructing elements to recover both layers. We show that the proposed approach learned from synthetically generated data performs well to real images.
  arXiv  Detail & Related papers  (2020-08-11T17:59:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.