DifIISR: A Diffusion Model with Gradient Guidance for Infrared Image Super-Resolution

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Xingyuan, Wang, Zirui, Zou, Yang, Chen, Zhixin, Ma, Jun, Jiang, Zhiying, Ma, Long, Liu, Jinyuan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909521135271936
author Li, Xingyuan
Wang, Zirui
Zou, Yang
Chen, Zhixin
Ma, Jun
Jiang, Zhiying
Ma, Long
Liu, Jinyuan
author_facet Li, Xingyuan
Wang, Zirui
Zou, Yang
Chen, Zhixin
Ma, Jun
Jiang, Zhiying
Ma, Long
Liu, Jinyuan
contents 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/DifIISR
format Preprint
id arxiv_https___arxiv_org_abs_2503_01187
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DifIISR: A Diffusion Model with Gradient Guidance for Infrared Image Super-Resolution
Li, Xingyuan
Wang, Zirui
Zou, Yang
Chen, Zhixin
Ma, Jun
Jiang, Zhiying
Ma, Long
Liu, Jinyuan
Computer Vision and Pattern Recognition
68T45
I.4.3
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/DifIISR
title DifIISR: A Diffusion Model with Gradient Guidance for Infrared Image Super-Resolution
topic Computer Vision and Pattern Recognition
68T45
I.4.3
url https://arxiv.org/abs/2503.01187