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

2026-03-17

AI Summary

This work addresses the critical issue of key information loss in overexposed regions prevalent in existing infrared and visible image fusion methods. To this end, we propose an exposure-aware progressive optimization fusion model that leverages a guidance module to extract fine-grained infrared features from overexposed areas, integrates them through a multi-scale context-aware iterative decoder to progressively enhance fusion quality, and employs an adaptive loss function to dynamically balance modality contributions under varying exposure conditions. We further introduce the first high-quality infrared-visible overexposure dataset (IVOE) to facilitate training and evaluation. Experimental results demonstrate that our method not only preserves visual fidelity in non-overexposed regions but also significantly improves the recovery of infrared cues in overexposed areas, outperforming state-of-the-art approaches and enhancing downstream task performance.

Technology Category

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

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing

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.

Problem

• infrared and visible image fusion
• overexposure
• highly bright regions
• visual information loss
• exposure awareness

Innovation

• exposure-aware fusion
• infrared-visible image fusion
• overexposure handling
• multiscale context fusion
• adaptive loss function