Quaternion Infrared Visible Image Fusion

2025-05-05

AI Summary

To address the challenges of poor color fidelity, insufficient exploitation of chromatic-structural information, and performance degradation in infrared–visible image fusion under low-visibility conditions, this paper proposes the first end-to-end quaternion-domain fusion framework. Methodologically, we design a quaternion-based low-visibility feature learning model, incorporating quaternion adaptive unsharp masking and a hierarchical Bayesian fusion mechanism to jointly model and adaptively enhance thermal target saliency and textural details. Our approach innovatively integrates quaternion convolution, multi-scale feature coupling, and Bayesian inference into a unified architecture, overcoming the limitations of conventional RGB-domain methods—namely, weak chromatic-structural modeling capability and poor robustness to degraded inputs. Extensive experiments on multiple low-visibility benchmarks demonstrate state-of-the-art performance, with significant improvements in thermal target fidelity, texture clarity, and illumination uniformity of fused results.

Technology Category

• Computer Vision: Multi-modal Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Querying, indexing, and retrieval in Web-related graphs

Abstract

Visible images provide rich details and color information only under well-lighted conditions while infrared images effectively highlight thermal targets under challenging conditions such as low visibility and adverse weather. Infrared-visible image fusion aims to integrate complementary information from infrared and visible images to generate a high-quality fused image. Existing methods exhibit critical limitations such as neglecting color structure information in visible images and performance degradation when processing low-quality color-visible inputs. To address these issues, we propose a quaternion infrared-visible image fusion (QIVIF) framework to generate high-quality fused images completely in the quaternion domain. QIVIF proposes a quaternion low-visibility feature learning model to adaptively extract salient thermal targets and fine-grained texture details from input infrared and visible images respectively under diverse degraded conditions. QIVIF then develops a quaternion adaptive unsharp masking method to adaptively improve high-frequency feature enhancement with balanced illumination. QIVIF further proposes a quaternion hierarchical Bayesian fusion model to integrate infrared saliency and enhanced visible details to obtain high-quality fused images. Extensive experiments across diverse datasets demonstrate that our QIVIF surpasses state-of-the-art methods under challenging low-visibility conditions.

Problem

• Integrate infrared and visible images for better fusion quality
• Address color structure neglect in visible image fusion
• Enhance performance with low-quality color-visible inputs

Innovation

• Quaternion domain fusion for infrared-visible images
• Adaptive feature learning in degraded conditions
• Hierarchical Bayesian fusion for enhanced details