Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Zhiwei Wang, Yayu Zheng, Defeng He, Li Zhao, Xiaoqin Zhang, Yuxing Li, Edmund Y. Lam

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.

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

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.
Paper Structure (32 sections, 15 equations, 11 figures, 7 tables)

This paper contains 32 sections, 15 equations, 11 figures, 7 tables.

Table of Contents

  1. Introduction
  2. Related Works
  3. Gnerative prior-based Image Fusion
  4. Handcrafted loss-guided Image Fusion
  5. Down-stream task-guided Image Fusion
  6. Infrared and visible image dataset
  7. Methodlogy
  8. Problem Formulation
  9. Exposure Guided Fusion Framework
  10. Iterative Decoding Fusion Module
  11. Iterative Refinement Mechanism
  12. Multi-Scale Context Fusion Module
  13. Infrared-Visible Over-Exposure Dataset
  14. Loss Function
  15. Experments
  16. ...and 17 more sections

Figures (11)

  • Figure 1: (I) Generative prior-based framework. (II) Downstream task-guided approache. (III–IV) Handcrafted loss-guided strategies: (III) texture-dominated optimization and (IV) intensity-dominated optimization.
  • Figure 2: The overall framework of EPOFusion, showing its main components and processing flow.
  • Figure 3: An overview of the infrared-visible overexposure (IVOE) dataset construction pipeline.
  • Figure 4: Examples from the IVOE dataset. The training set is synthetically generated with accurate annotations, and the test set is collected from multiple public datasets.
  • Figure 5: The architecture of the Multi-Scale Context Fusion Module (MSCF).
  • ...and 6 more figures