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

2026-03-22

AI Summary

This work addresses the challenge of geometric distortion and artifacts caused by defocus blur in multi-focus image fusion. To this end, we propose the first strictly rotation-equivariant, end-to-end diffusion-based fusion model, which embeds rotation equivariance directly into the diffusion network to effectively preserve directional consistency of image geometric structures. Our approach not only introduces strict rotation equivariance to this task for the first time but also provides a theoretical analysis to quantify equivariance error. Experimental results demonstrate that the proposed method consistently outperforms existing approaches across four benchmark datasets, achieving performance gains of 0.28% to 6.64% on six evaluation metrics.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Multi-instance/Multi-view Learning

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

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.

Problem

• multi-focus image fusion
• defocus blur
• geometric structures
• image artifacts
• rotation equivariance

Innovation

• rotation equivariance
• diffusion model
• multi-focus image fusion
• geometric consistency
• equivariant architecture