Boosting Weakly Convex Ridge Regularizers with Spatial Adaptivity

Abstract

We propose to enhance 1-weakly convex ridge regularizers for image reconstruction by incorporating spatial adaptivity. To this end, we resort to a neural network that generates a weighting mask from an initial reconstruction, which is obtained with the baseline regularizer. Empirically, the learned mask can capture long-range dependencies and leads to a smaller penalization of inherent image structures. Our experiments show that spatial adaptivity improves the performance of image denoising and MRI reconstruction.

PDF NeurIPSW OpenReview Semantic Scholar

Cite

Text

Neumayer et al. "Boosting Weakly Convex Ridge Regularizers with Spatial Adaptivity." NeurIPS 2023 Workshops: Deep_Inverse, 2023.

Markdown

[Neumayer et al. "Boosting Weakly Convex Ridge Regularizers with Spatial Adaptivity." NeurIPS 2023 Workshops: Deep_Inverse, 2023.](https://mlanthology.org/neuripsw/2023/neumayer2023neuripsw-boosting/)

BibTeX

@inproceedings{neumayer2023neuripsw-boosting,
  title     = {{Boosting Weakly Convex Ridge Regularizers with Spatial Adaptivity}},
  author    = {Neumayer, Sebastian and Pourya, Mehrsa and Goujon, Alexis and Unser, Michael},
  booktitle = {NeurIPS 2023 Workshops: Deep_Inverse},
  year      = {2023},
  url       = {https://mlanthology.org/neuripsw/2023/neumayer2023neuripsw-boosting/}
}