Revisiting Single Image Super-Resolution Under Internet Environment: Blur Kernels and Reconstruction Algorithms

22 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Designing a Practical Degradation Model for Deep Blind Image Super-Resolution (2021, methodology): “As mentioned in the introduction, existing DNNs-based SISR methods are generally based on bicubic downsampling [23, 44] and traditional degradations [26, 37, 54, 59, 60], or some simple variants [11, 41, 53, 56, 58].”
Learning Deep CNN Denoiser Prior for Image Restoration (2017, background): “This makes the learned model deteriorates seriously when the blur kernel adopted in training deviates from the real one [23, 64].”
Plug-and-Play Image Restoration With Deep Denoiser Prior (2020, methodology): “…are mainly designed for bicubic degradation model with the following formulation where ↓ bicubics denotes bicubic downsamling with down-scaling factor s , it has been revealed that these methods would deteriorate seriously if the real degradation model deviates from the assumed one [79], [80].”
Learning a Single Convolutional Super-Resolution Network for Multiple Degradations (2017, background): “Existing literatures have considered two types of downsamplers, including direct downsampler [11, 17, 36, 51, 55] and bicubic downsampler [7, 12, 14, 15, 47, 52].”