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

TL;DR

ReDiffuse introduces a rotation-equivariant diffusion model for multi-focus image fusion, effectively preserving structural details and orientations, leading to improved fusion quality across multiple datasets.

Contribution

The paper presents the first end-to-end rotation-equivariant diffusion model for MFIF, with theoretical analysis and superior performance over existing methods.

Findings

ReDiffuse achieves 0.28-6.64% improvement in evaluation metrics.

The model maintains structural consistency and orientation in fused images.

It demonstrates competitive performance across four diverse datasets.

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.