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

2025-03-03

AI Summary

Infrared (IR) images suffer from low resolution and complex degradations, limiting their utility in autonomous driving and robotic perception; existing infrared image super-resolution (IISR) methods fail to jointly preserve modality-specific characteristics and satisfy downstream task requirements. This paper proposes DifIISR, a perception-optimized diffusion-based IISR framework. Its core innovations include: (i) the first introduction of thermal-spectrum distribution constraints to model IR-specific frequency-domain priors; (ii) a multi-vision-foundation-model–guided gradient injection mechanism—leveraging detection- and segmentation-oriented models—to steer reverse diffusion with task-aware gradients; and (iii) noise-adaptive regulation to enhance reconstruction fidelity and cross-scenario generalization. Extensive experiments demonstrate that DifIISR achieves state-of-the-art performance in both quantitative metrics (PSNR/SSIM) and downstream perception tasks (object detection and semantic segmentation), effectively bridging the gap between reconstruction quality and machine perception.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Imitation Learning & Inverse Reinforcement Learning

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

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/DifIISR

Problem

• Improves infrared image super-resolution for better visual quality.
• Addresses unique modal characteristics of infrared imaging.
• Enhances perceptual performance for downstream visual tasks.

Innovation

• Diffusion model with gradient guidance
• Infrared thermal spectrum regulation
• Visual foundational models for perception