DifIISR: A Diffusion Model with Gradient Guidance for Infrared Image Super-Resolution
Authors:
Top Cited Papers
- 10 June 2025
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 7534-7544
Abstract
Infrared imaging is essential for autonomous driving and robotic operations as a supportive modality due to its reliable performance in challenging environments. Despite its popularity, the limitations of infrared cameras, such as low spatial resolution and complex degradations, consistently challenge imaging quality and subsequent visual tasks. Hence, infrared image super-resolution (IISR) has been developed to address this challenge. While recent developments in diffusion models have greatly advanced this field, current methods to solve it either ignore the unique modal characteristics of infrared imaging or overlook the machine perception requirements. To bridge these gaps, we propose DifIISR, an infrared image super-resolution diffusion model optimized for visual quality and perceptual performance. Our approach achieves task-based guidance for diffusion by injecting gradients derived from visual and perceptual priors into the noise during the reverse process. Specifically, we introduce an infrared thermal spectrum distribution regulation to preserve visual fidelity, ensuring that the reconstructed infrared images closely align with high-resolution images by matching their frequency components. Subsequently, we incorporate various visual foundational models as the perceptual guidance for downstream visual tasks, infusing generalizable perceptual features beneficial for detection and segmentation. As a result, our approach gains superior visual results while attaining State-Of-The-Art downstream task performance. Code is available at https://github.com/zirui0625/DifIISRKeywords
All Related Versions
Funding Information
- National Natural Science Foundation of China
- China Postdoctoral Science Foundation
This publication has 47 references indexed in Scilit:
- Contourlet Residual for Prompt Learning Enhanced Infrared Image Super-Resolution2024
- Navigation Instruction Generation with BEV Perception and Large Language Models2024
- RAW-Adapter: Adapting Pre-trained Visual Model to Camera RAW Images2024
- An interactively reinforced paradigm for joint infrared-visible image fusion and saliency object detectionInformation Fusion, 2023
- Efficient Long-Range Attention Network for Image Super-Resolution2022
- LatticeNet: Towards Lightweight Image Super-Resolution with Lattice Block2020
- Multi-scale Residual Network for Image Super-Resolution2018
- Image Super-Resolution Using Very Deep Residual Channel Attention Networks2018
- The TNO Multiband Image Data CollectionData in Brief, 2017
- Learning a Deep Convolutional Network for Image Super-Resolution2014