Spatially-Variant Degradation Model for Dataset-Free Super-Resolution

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 (2×).Code will be released at https: //github.com/DeepMed-Lab-ECNU/SVDSR

Cite

Text

Guo et al. "Spatially-Variant Degradation Model for Dataset-Free Super-Resolution." Proceedings of the European Conference on Computer Vision (ECCV), 2024. doi:10.1007/978-3-031-72698-9_20

Markdown

[Guo et al. "Spatially-Variant Degradation Model for Dataset-Free Super-Resolution." Proceedings of the European Conference on Computer Vision (ECCV), 2024.](https://mlanthology.org/eccv/2024/guo2024eccv-spatiallyvariant/) doi:10.1007/978-3-031-72698-9_20

BibTeX

@inproceedings{guo2024eccv-spatiallyvariant,
  title     = {{Spatially-Variant Degradation Model for Dataset-Free Super-Resolution}},
  author    = {Guo, Shaojie and Song, Haofei and Li, Qingli and Wang, Yan},
  booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
  year      = {2024},
  doi       = {10.1007/978-3-031-72698-9_20},
  url       = {https://mlanthology.org/eccv/2024/guo2024eccv-spatiallyvariant/}
}