2018 · 41 citations · 26 references
ComputingComputer ScienceComputer VisionFeature EngineeringMachine VisionDeep LearningImage QualitySpatial ResolutionBenchmark DatasetsConvolutional Neural NetworksImage Super-resolutionResidual LayerResidual NetworksSpatial ContextSuper-resolutionUpscaling
This paper proposes a method, Dense ByNet, for single image super-resolution based on a convolutional neural network (CNN). The main innovation is a new architecture that combines several CNN design choices. Using a residual network as a basis, it introduces dense connections inside residual blocks, significantly reducing the number of parameters. Second, we apply dilation convolutions to increase the spatial context. Lastly, we propose modifications to the activation and cost functions. We evaluate the method on benchmark datasets and show that it achieves state-of-the-art results over multiple upscaling factors in terms of peak SNR and structural similarity (SSIM).
26
Deep Residual Learning for Image Recognition
Kaiming He, Xiangyu Zhang, Shaoqing Ren et al. · 2016 · 222.1K citations · Full text
Densely Connected Convolutional Networks
Gao Huang, Zhuang Liu, Laurens van der Maaten et al. · 2017 · 44.7K citations
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
Kaiming He, Xiangyu Zhang, Shaoqing Ren et al. · 2015 · 18.8K citations