RPT-SR: Regional Prior attention Transformer for infrared image Super-Resolution

TL;DR

RPT-SR introduces a novel attention mechanism that incorporates persistent scene priors into infrared image super-resolution, significantly improving performance across diverse datasets by leveraging scene layout information.

Contribution

The paper proposes a dual-token attention framework that explicitly encodes scene priors into a Transformer for infrared super-resolution, enhancing efficiency and accuracy.

Findings

Achieves state-of-the-art results on LWIR and SWIR datasets.

Effectively utilizes scene priors to improve super-resolution quality.

Demonstrates broad applicability across different infrared spectra.

Abstract

General-purpose super-resolution models, particularly Vision Transformers, have achieved remarkable success but exhibit fundamental inefficiencies in common infrared imaging scenarios like surveillance and autonomous driving, which operate from fixed or nearly-static viewpoints. These models fail to exploit the strong, persistent spatial priors inherent in such scenes, leading to redundant learning and suboptimal performance. To address this, we propose the Regional Prior attention Transformer for infrared image Super-Resolution (RPT-SR), a novel architecture that explicitly encodes scene layout information into the attention mechanism. Our core contribution is a dual-token framework that fuses (1) learnable, regional prior tokens, which act as a persistent memory for the scene's global structure, with (2) local tokens that capture the frame-specific content of the current input. By utilizing these tokens into an attention, our model allows the priors to dynamically modulate the local reconstruction process. Extensive experiments validate our approach. While most prior works focus on a single infrared band, we demonstrate the broad applicability and versatility of RPT-SR by establishing new state-of-the-art performance across diverse datasets covering both Long-Wave (LWIR) and Short-Wave (SWIR) spectra