RESUMO
This paper presents a transfer domain strategy to tackle the limitations of low-resolution thermal sensors and generate higher-resolution images of reasonable quality. The proposed technique employs a CycleGAN architecture and uses a ResNet as an encoder in the generator along with an attention module and a novel loss function. The network is trained on a multi-resolution thermal image dataset acquired with three different thermal sensors. Results report better performance benchmarking results on the 2nd CVPR-PBVS-2021 thermal image super-resolution challenge than state-of-the-art methods. The code of this work is available online.
Assuntos
Algoritmos , Processamento de Imagem Assistida por Computador , Processamento de Imagem Assistida por Computador/métodos , Imageamento por Ressonância Magnética/métodosRESUMO
OBJECTIVE: The goal of super-resolution is to generate high-resolution images from low-resolution input images. METHODS: In this paper, a combined method based on sparse signal representation and adaptive M-estimator is proposed for single-image super-resolution. With the sparse signal representation, the correlation between the sparse representation of high-resolution patches and that of low-resolution patches for the identical image is learned as a set of joint dictionaries and a set of high-resolution patches is obtained for high- and low-resolution patches. Then the dictionaries and high-resolution patches are used to produce the high-resolution image for a low-resolution single image. RESULTS: At the post-processing phase, the adaptive M-estimator, combining the advantages of traditional L1 and L2 norms, is used to give further processing for the resultant high-resolution image, to reduce the artefact by learning and reconstitution, and improve the performance. CONCLUSION: Three experimental results show the performance improvement of the proposed algorithm over other methods.