EPOFusion: Exposure aware Progressive Optimization Method for Infrared and Visible Image Fusion

TL;DR

EPOFusion is a novel infrared and visible image fusion method that enhances overexposed regions by introducing exposure-aware modules and a new dataset, improving visual quality and task performance.

Contribution

The paper presents EPOFusion, the first exposure-aware fusion model with a guidance module, iterative decoder, adaptive loss, and a new overexposure dataset for infrared-visible image fusion.

Findings

EPOFusion outperforms existing methods in overexposed regions.

It maintains infrared cues in overexposed areas while ensuring visual fidelity.

The method improves downstream task performance.

Abstract

Overexposure frequently occurs in practical scenarios, causing the loss of critical visual information. However, existing infrared and visible fusion methods still exhibit unsatisfactory performance in highly bright regions. To address this, we propose EPOFusion, an exposure-aware fusion model. Specifically, a guidance module is introduced to facilitate the encoder in extracting fine-grained infrared features from overexposed regions. Meanwhile, an iterative decoder incorporating a multiscale context fusion module is designed to progressively enhance the fused image, ensuring consistent details and superior visual quality. Finally, an adaptive loss function dynamically constrains the fusion process, enabling an effective balance between the modalities under varying exposure conditions. To achieve better exposure awareness, we construct the first infrared and visible overexposure dataset (IVOE) with high quality infrared guided annotations for overexposed regions. Extensive experiments show that EPOFusion outperforms existing methods. It maintains infrared cues in overexposed regions while achieving visually faithful fusion in non-overexposed areas, thereby enhancing both visual fidelity and downstream task performance. Code, fusion results and IVOE dataset will be made available at https://github.com/warren-wzw/EPOFusion.git.