2020 · 28 citations · 14 references
ComputingComputer ScienceComputer VisionDigital ImagingMachine LearningAttention NetworksDeep LearningRepresentation LearningBase UnitsConvolutionImage Similarity MeasurementImage Super-resolutionSuper-resolutionSuper-resolution ImagingSuper-resolution Processing
This paper proposes a novel architecture for thermal image super-resolution. A very large dataset is provided by PBVS 2020 in their super-resolution challenge. This dataset contains the images with three different resolution scales(low, medium, high) [1]. This dataset is used to train the proposed architecture to generate the super-resolution images in x2, x3, x4 scales. The proposed architecture is based on the residual blocks as the base units of the network. Along with this, the coordinate convolution layer and the convolutional block attention Module (CBAM) are also used in the architecture. Further, the multi-level supervision is implemented to supervise the output image resolution similarity with the real image at each block during training. To test the robustness of the proposed model, we evaluated our model on the Thermal-6 dataset [13]. The results show that our model is efficient to achieve the state of art results on the PBVS'2020 dataset. Further the results on the Thermal-6 dataset show that the model has a decent generalization capacity.
14
Deep Residual Learning for Image Recognition
Kaiming He, Xiangyu Zhang, Shaoqing Ren et al. · 2016 · 222.1K citations · Full text
Image quality assessment: from error visibility to structural similarity
Zhou Wang, Alan C. Bovik, Hamid R. Sheikh et al. · IEEE Transactions on Image Processing · 2004 · 56K citations
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
Christian Ledig, Lucas Theis, Ferenc Huszár et al. · 2017 · 12.3K citations