English

Spatially-Variant Degradation Model for Dataset-free Super-resolution

Image and Video Processing 2024-07-12 v1 Computer Vision and Pattern Recognition

Abstract

This paper focuses on the dataset-free Blind Image Super-Resolution (BISR). Unlike existing dataset-free BISR methods that focus on obtaining a degradation kernel for the entire image, we are the first to explicitly design a spatially-variant degradation model for each pixel. Our method also benefits from having a significantly smaller number of learnable parameters compared to data-driven spatially-variant BISR methods. Concretely, each pixel's degradation kernel is expressed as a linear combination of a learnable dictionary composed of a small number of spatially-variant atom kernels. The coefficient matrices of the atom degradation kernels are derived using membership functions of fuzzy set theory. We construct a novel Probabilistic BISR model with tailored likelihood function and prior terms. Subsequently, we employ the Monte Carlo EM algorithm to infer the degradation kernels for each pixel. Our method achieves a significant improvement over other state-of-the-art BISR methods, with an average improvement of 1 dB (2x).Code will be released at https://github.com/shaojieguoECNU/SVDSR.

Keywords

Cite

@article{arxiv.2407.08252,
  title  = {Spatially-Variant Degradation Model for Dataset-free Super-resolution},
  author = {Shaojie Guo and Haofei Song and Qingli Li and Yan Wang},
  journal= {arXiv preprint arXiv:2407.08252},
  year   = {2024}
}
R2 v1 2026-06-28T17:36:51.066Z