Bilateral Network with Channel Splitting Network and Transformer for Thermal Image Super-Resolution

TL;DR

This paper introduces a novel bilateral network architecture with channel splitting and transformer modules for thermal image super-resolution, achieving high-quality results in the PBVS-2022 challenge.

Contribution

It proposes a new network design combining channel splitting, transformers, and feature fusion modules specifically for thermal image super-resolution.

Findings

Achieved PSNR=33.64 and SSIM=0.9263 for x4 super-resolution.

Achieved PSNR=21.08 and SSIM=0.7803 for x2 super-resolution.

Outperformed previous methods in the PBVS-2022 challenge.

Abstract

In recent years, the Thermal Image Super-Resolution (TISR) problem has become an attractive research topic. TISR would been used in a wide range of fields, including military, medical, agricultural and animal ecology. Due to the success of PBVS-2020 and PBVS-2021 workshop challenge, the result of TISR keeps improving and attracts more researchers to sign up for PBVS-2022 challenge. In this paper, we will introduce the technical details of our submission to PBVS-2022 challenge designing a Bilateral Network with Channel Splitting Network and Transformer(BN-CSNT) to tackle the TISR problem. Firstly, we designed a context branch based on channel splitting network with transformer to obtain sufficient context information. Secondly, we designed a spatial branch with shallow transformer to extract low level features which can preserve the spatial information. Finally, for the context branch in order to fuse the features from channel splitting network and transformer, we proposed an attention refinement module, and then features from context branch and spatial branch are fused by proposed feature fusion module. The proposed method can achieve PSNR=33.64, SSIM=0.9263 for x4 and PSNR=21.08, SSIM=0.7803 for x2 in the PBVS-2022 challenge test dataset.