Clarity Contrast and Similarity Selection for Multi-Focus Image Fusion

2026-08-04

AI Summary

This work addresses the limitations of existing multi-focus image fusion methods, which often produce blurry boundaries and lack interpretability due to insufficient explicit interaction between source images. To overcome these issues, we propose the Clarity-aware Contrast and Similarity Selection Network (CSNet), which introduces, for the first time, a Clarity Contrast Attention Module (CCAM) to enhance sharp features while suppressing defocused regions. CSNet further incorporates a similarity-based selection strategy to refine boundary pixels. By explicitly modeling the defocus diffusion effect, our method enables direct inter-image interaction, accurately localizing in-focus regions and recovering natural boundaries. Extensive experiments demonstrate that CSNet achieves state-of-the-art performance in both quantitative metrics and qualitative visual assessment, effectively generating high-quality, spatially coherent all-in-focus images.

Abstract

Multi-focus image fusion (MFIF) aims to generate an all-in-focus image from multiple images of the same scene focused at different regions. Most existing deep learning-based methods lack explicit interaction between the source images, which limits their performance and interpretability. This paper presents a novel Clarity Contrast and Similarity Selection Network (CSNet), to bridge direct information exchange for MFIF. Specifically, by contrasting the clarity differences between source images within our proposed Clarity Contrast Attention Module (CCAM), we mutually enhance sharp features while suppressing blurry ones. This allows us to identify the exactly focused regions in each source and locate the focused-defocused boundaries. Moreover, the Defocus Spread Effect (DSE) degrades pixels in all source images around the boundaries. To further refine these ambiguous areas, we introduce a Similarity Selection Strategy, which reconstructs an initial clear image from source images and selects optimal pixels by comparing the similarity among them. Through this interactive approach, CSNet effectively preserves focused regions as well as recovering natural boundaries to fuse an all-in-focus output. Extensive experiments demonstrate that our method achieves state-of-the-art performance both quantitatively and qualitatively. Our code is available on Github: https://github.com/ZYC-HUST/CSNet.

Problem

• Multi-focus image fusion
• Clarity contrast
• Defocus spread effect
• Focused-defocused boundaries
• Image fusion

Innovation

• Clarity Contrast Attention Module
• Similarity Selection Strategy
• Defocus Spread Effect
• Multi-focus Image Fusion
• All-in-focus Image