cs.CVNov 11, 2026

Image Deblending with Diffusion Models

Authors: Dan Botchan, Ohad Fried, Yacov Hel-Or

Organizations: Reichman University, Herzliya, Israel

Abstract

Image deblending is the task of decomposing a composite image back into its source images, which is an ill-posed problem, as a single blended image can be decomposed into multiple plausible source layers. While diffusion models are often used to solve inverse problems, they typically address single-output reconstruction problems. In this work, we formulate deblending as a joint inverse problem, employing diffusion posterior sampling to simultaneously reconstruct two source images, demonstrating that a single diffusion prior is expressive enough to disentangle two full images at once rather than just one. Drawing inspiration from human perception, where semantic understanding helps disentangle visual inconsistencies, we propose a training-free framework that leverages text prompts to constrain this solution space. We address the blind deblending task through a two-stage architecture: text-guided latent diffusion performs semantic separation using prompts as high-level cues, followed by a pixel-space refinement to recover fine details. Stochastic sampling produces multiple plausible decompositions that can be ranked without ground truth. Extensive experiments show that our training-free method achieves state-of-the-art results on unseen domains and extends to spatially-varying alpha maps, while remaining competitive with supervised baselines on standard scalar blending benchmarks.

Figures & tables

Appendix figures & tables14 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Frequency-Decoupled Diffusion Guidance for Non-Blind Image Deblurring

    Oct 5, 2026Sihan Wang, Jinshu Huang, Haibin Su +1Image DeblurringFrequency-Domain Image Processing

  2. Rectify Then Diffuse: Disentangling Concepts Before Denoising Trajectory Unfolds

    Aug 4, 2026Ning Zhu, An Chen, Mengfei Zhao +4T2I GenerationAttention Control in Diffusion Models

  3. Controllable blind deblurring with diffusion models

    Aug 24, 2026Imane Si Salah, Emile Cribelier, Thomas Veit +2Image DeblurringImage Restoration