Texture and Noise Dual Adaptation for Infrared Image Super-Resolution

TL;DR

This paper introduces DASRGAN, a novel IR super-resolution framework that enhances texture details while effectively reducing noise and artifacts through dual domain adaptation techniques.

Contribution

The paper proposes a dual adaptation framework with specialized modules for texture enhancement and noise suppression, advancing IR super-resolution performance.

Findings

DASRGAN outperforms existing methods on multiple benchmarks.

The texture-oriented adaptation improves detail fidelity.

Noise-oriented adaptation reduces noise artifacts effectively.

Abstract

Recent efforts have explored leveraging visible light images to enrich texture details in infrared (IR) super-resolution. However, this direct adaptation approach often becomes a double-edged sword, as it improves texture at the cost of introducing noise and blurring artifacts. To address these challenges, we propose the Target-oriented Domain Adaptation SRGAN (DASRGAN), an innovative framework specifically engineered for robust IR super-resolution model adaptation. DASRGAN operates on the synergy of two key components: 1) Texture-Oriented Adaptation (TOA) to refine texture details meticulously, and 2) Noise-Oriented Adaptation (NOA), dedicated to minimizing noise transfer. Specifically, TOA uniquely integrates a specialized discriminator, incorporating a prior extraction branch, and employs a Sobel-guided adversarial loss to align texture distributions effectively. Concurrently, NOA utilizes a noise adversarial loss to distinctly separate the generative and Gaussian noise pattern distributions during adversarial training. Our extensive experiments confirm DASRGAN's superiority. Comparative analyses against leading methods across multiple benchmarks and upsampling factors reveal that DASRGAN sets new state-of-the-art performance standards. Code are available at \url{https://github.com/yongsongH/DASRGAN}.