GPSMamba: A Global Phase and Spectral Prompt-guided Mamba for Infrared Image Super-Resolution

2025-07-25

AI Summary

Infrared image super-resolution (IRSR) suffers from low contrast and sparse texture, necessitating long-range dependency modeling to ensure global structural consistency. Existing Mamba-based state space models are constrained by 1D causal scanning, which compromises 2D spatial context integrity. To address this, we propose a spectrum-phase-guided non-causal Mamba architecture. Specifically, we design an adaptive semantic-frequency state space module that injects frequency-domain priors into hidden states; integrate thermal-spectrum attention to enhance global contextual awareness; and introduce a phase-consistency loss to enforce spectral fidelity in reconstruction. By abandoning conventional causal constraints, our approach enables holistic 2D feature modeling. Extensive experiments on multiple infrared benchmarks demonstrate state-of-the-art performance, with significant improvements in perceptual sharpness, structural preservation, and spectral accuracy.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Large Multimodal Models (LMMs)
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• 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 Image Super-Resolution (IRSR) is challenged by the low contrast and sparse textures of infrared data, requiring robust long-range modeling to maintain global coherence. While State-Space Models like Mamba offer proficiency in modeling long-range dependencies for this task, their inherent 1D causal scanning mechanism fragments the global context of 2D images, hindering fine-detail restoration. To address this, we propose Global Phase and Spectral Prompt-guided Mamba (GPSMamba), a framework that synergizes architectural guidance with non-causal supervision. First, our Adaptive Semantic-Frequency State Space Module (ASF-SSM) injects a fused semantic-frequency prompt directly into the Mamba block, integrating non-local context to guide reconstruction. Then, a novel Thermal-Spectral Attention and Phase Consistency Loss provides explicit, non-causal supervision to enforce global structural and spectral fidelity. By combining these two innovations, our work presents a systematic strategy to mitigate the limitations of causal modeling. Extensive experiments demonstrate that GPSMamba achieves state-of-the-art performance, validating our approach as a powerful new paradigm for infrared image restoration. Code is available at https://github.com/yongsongH/GPSMamba.

Problem

• Enhance infrared image resolution with global coherence
• Overcome 1D causal scanning limitations in 2D image restoration
• Integrate spectral and phase guidance for structural fidelity

Innovation

• Adaptive Semantic-Frequency State Space Module
• Thermal-Spectral Attention and Phase Loss
• Global Phase and Spectral Prompt-guided Mamba