cs.CVOct 1, 2025

Blind Image Restoration via Merging the Manifold Hypothesis, Kernel Method and a Diffusion-like Flow

Authors: Leah Bar, Liron Mor Yosef, Shai Zucker, Neta Shoham, Inbar Seroussi, Nir Sochen

Organizations: Department of Applied Mathematics, Tel Aviv University, Tel Aviv, Israel

Abstract

Blind Image Restoration (BIR) aims to restore degraded images without knowledge of either the type or severity of the degradation. This is a challenging ill-posed inverse problem for which an image prior is essential. We view the prior of an image class as a probability distribution supported on a low-dimensional manifold embedded in the high-dimensional image space. Existing generative approaches primarily model the probability distribution, while the geometric structure is implicit or disregarded. Conversely, geometric approaches do not account for the non-uniform probability distribution on the manifold. We propose a geometric-probabilistic framework for BIR that models these aspects. The probability distribution on the manifold is approximated using a kernel-based method, while a distance from the manifold function induces a geometry-based probability function on the ambient space. This formulation leads to the (Latent) Manifold-Probabilistic Projection Model ((L)MPPM), a restoration model defined in both image and latent spaces. (L)MPPM induces a flow guided by a score field that jointly incorporates geometric and probabilistic information. Evaluated on image restoration tasks and datasets, (L)MPPM consistently outperforms existing approaches, providing empirical evidence for the benefit of incorporating both geometric and probabilistic information into the image prior.

Figures & tables

Appendix figures & tables12 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Geodesic Flow Matching on a Riemannian Degradation Manifold for Blind Image Restoration

    Jun 4, 2026Akshay Janardan Bankar, Ankita Chatterjee, Sayan Banerjee +3Flow MatchingRiemannian Flow Matching

  2. Flow Straight to Reality: Perceptually Consistent Flow Matching for Efficient Image Restoration

    Aug 11, 2026Sangwoo Jo, Donggeun Ko, Jayeon Kang +3Flow MatchingPerceptual Loss

  3. IR-Flow: Bridging Discriminative and Generative Image Restoration via Rectified Flow

    Apr 21, 2026Zihao Fan, Xin Lu, Jie Xiao +3Rectified FlowAll-in-One Image Restoration