ReDiffuse: Rotation Equivariant Diffusion Model for Multi-focus Image Fusion

• URL: http://arxiv.org/abs/2603.21129v1
• Date: Sun, 22 Mar 2026 08:52:41 GMT
• Title: ReDiffuse: Rotation Equivariant Diffusion Model for Multi-focus Image Fusion
• Abstract summary: A key challenge in applying diffusion models to the ill-posed MFIF problem is that defocus blur can make common symmetric geometric structures appear warped and deformed.<n>We propose ReDiffuse, a rotation-equivariant diffusion model for MFIF.<n>We show that ReDiffuse achieves competitive performance, with improvements of 0.28-6.64% across six evaluation metrics.
• Score: 14.433659465575586
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Diffusion models have achieved impressive performance on multi-focus image fusion (MFIF). However, a key challenge in applying diffusion models to the ill-posed MFIF problem is that defocus blur can make common symmetric geometric structures (e.g., textures and edges) appear warped and deformed, often leading to unexpected artifacts in the fused images. Therefore, embedding rotation equivariance into diffusion networks is essential, as it enables the fusion results to faithfully preserve the original orientation and structural consistency of geometric patterns underlying the input images. Motivated by this, we propose ReDiffuse, a rotation-equivariant diffusion model for MFIF. Specifically, we carefully construct the basic diffusion architectures to achieve end-to-end rotation equivariance. We also provide a rigorous theoretical analysis to evaluate its intrinsic equivariance error, demonstrating the validity of embedding equivariance structures. ReDiffuse is comprehensively evaluated against various MFIF methods across four datasets (Lytro, MFFW, MFI-WHU, and Road-MF). Results demonstrate that ReDiffuse achieves competitive performance, with improvements of 0.28-6.64\% across six evaluation metrics. The code is available at https://github.com/MorvanLi/ReDiffuse.

Related papers

• Reversible Efficient Diffusion for Image Fusion [66.35113261837469]
  Multi-modal image fusion aims to consolidate complementary information from diverse source images into a unified representation.<n>While diffusion models have demonstrated impressive generative capabilities in image generation, they often suffer from detail loss when applied to image fusion tasks.<n>This issue arises from the accumulation of noise errors inherent in the Markov process, leading to inconsistency and degradation in the fused results.<n>We propose the Reversible Efficient Diffusion (RED) model - an explicitly supervised training framework that inherits the powerful generative capability of diffusion models while avoiding the distribution estimation.
  arXiv  Detail & Related papers  (2026-01-28T05:14:55Z)
• R-Meshfusion: Reinforcement Learning Powered Sparse-View Mesh Reconstruction with Diffusion Priors [6.102039677329314]
  Mesh reconstruction from multi-view images degrades significantly under sparse-view conditions.<n>Recent advances in diffusion models have demonstrated strong capabilities in synthesizing novel views from limited inputs.<n>We propose a novel framework that leverages diffusion models to enhance sparse-view mesh reconstruction in a principled and reliable manner.
  arXiv  Detail & Related papers  (2025-04-16T10:23:59Z)
• FaithDiff: Unleashing Diffusion Priors for Faithful Image Super-resolution [48.88184541515326]
  We propose a simple and effective method, named FaithDiff, to fully harness the power of latent diffusion models (LDMs) for faithful image SR.<n>In contrast to existing diffusion-based SR methods that freeze the diffusion model pre-trained on high-quality images, we propose to unleash the diffusion prior to identify useful information and recover faithful structures.
  arXiv  Detail & Related papers  (2024-11-27T23:58:03Z)
• Adaptive Multi-modal Fusion of Spatially Variant Kernel Refinement with Diffusion Model for Blind Image Super-Resolution [23.34647832483913]
  We introduce a framework known as Adaptive Multi-modal Fusion of textbfSpatially Variant Kernel Refinement with Diffusion Model for Blind Image textbfSuper-textbfResolution. We also introduce the Adaptive Multi-Modal Fusion (AMF) module to align the information from three modalities: low-resolution images, depth maps, and blur kernels.
  arXiv  Detail & Related papers  (2024-03-09T06:01:25Z)
• Hierarchical Integration Diffusion Model for Realistic Image Deblurring [71.76410266003917]
  Diffusion models (DMs) have been introduced in image deblurring and exhibited promising performance. We propose the Hierarchical Integration Diffusion Model (HI-Diff), for realistic image deblurring. Experiments on synthetic and real-world blur datasets demonstrate that our HI-Diff outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-05-22T12:18:20Z)
• Denoising Diffusion Models for Plug-and-Play Image Restoration [135.6359475784627]
  This paper proposes DiffPIR, which integrates the traditional plug-and-play method into the diffusion sampling framework. Compared to plug-and-play IR methods that rely on discriminative Gaussian denoisers, DiffPIR is expected to inherit the generative ability of diffusion models.
  arXiv  Detail & Related papers  (2023-05-15T20:24:38Z)
• 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)
• DDFM: Denoising Diffusion Model for Multi-Modality Image Fusion [144.9653045465908]
  We propose a novel fusion algorithm based on the denoising diffusion probabilistic model (DDPM) Our approach yields promising fusion results in infrared-visible image fusion and medical image fusion.
  arXiv  Detail & Related papers  (2023-03-13T04:06:42Z)
• MFIF-GAN: A New Generative Adversarial Network for Multi-Focus Image Fusion [29.405149234582623]
  Multi-Focus Image Fusion (MFIF) is a promising technique to obtain all-in-focus images. One of the research trends of MFIF is to avoid the defocus spread effect (DSE) around the focus/defocus boundary (FDB) We propose a network termed MFIF-GAN to generate focus maps in which the foreground region are correctly larger than the corresponding objects.
  arXiv  Detail & Related papers  (2020-09-21T09:36:34Z)

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.