Decoupling Cross-Modality Manifold Discrepancy: Leveraging Visible Diffusion Priors for Infrared Super-Resolution

2026-07-23

AI Summary

This work addresses the challenge in infrared image super-resolution of simultaneously preserving global distribution consistency, structural integrity, and high-quality generation—a balance that existing diffusion-based methods often fail to achieve due to either insufficient or excessive intervention. To this end, the authors propose Shift-IISR, a novel dual-path diffusion framework that explicitly decouples cross-modal manifold discrepancies. The approach introduces a Global Representation Modulation (GRM) module to leverage visible-spectrum priors for extracting modality-specific features that align global distributions, while a Local Structure Refinement (LSR) module is dynamically integrated at each denoising step to enhance structural consistency. Experimental results demonstrate that Shift-IISR significantly improves both distributional alignment and structural fidelity without compromising super-resolution performance.

Abstract

Infrared image super-resolution (IISR) mitigates the limitations imposed by low spatial resolution. Existing methods have recognized that IISR should preserve consistency in global distribution and structural information while enhancing image clarity. However, these methods are either insufficient or overly intrusive, a problem that becomes even more pronounced in diffusion-based models. To address these issues, we propose a dual-path diffusion-based framework for IISR, termed Shift-IISR. The proposed method is designed to improve the consistency of IISR results while preserving the generative capacity of diffusion models. Specifically, we develop a Global Representation Modulation (GRM) module to extract modality-specific information from infrared imagery and guide the global distribution of the diffusion model toward the ground truth. In addition, we introduce a Local Structure Refinement (LSR) module to encourage the model to focus on structural information at each step of the iterative denoising process. Extensive experiments demonstrate that the proposed method effectively improves distributional and structural consistency while maintaining competitive super-resolution performance. The source code of the proposed Shift-IISR can be available at https://github.com/Assassink8/Shift-IISR.

Problem

• Infrared Super-Resolution
• Cross-Modality
• Manifold Discrepancy
• Diffusion Models
• Structural Consistency

Innovation

• Infrared Super-Resolution
• Diffusion Models
• Cross-Modality Alignment
• Global Representation Modulation
• Local Structure Refinement