HyDRA: Hybrid Denoising Regularization for Measurement-Only DEQ Training
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914232901042176 |
|---|---|
| author | Haltmeier, Markus Neumann, Lukas Gruber, Nadja Schwab, Johannes Hwang, Gyeongha |
| author_facet | Haltmeier, Markus Neumann, Lukas Gruber, Nadja Schwab, Johannes Hwang, Gyeongha |
| contents | Solving image reconstruction problems of the form \(\mathbf{A} \mathbf{x} = \mathbf{y}\) remains challenging due to ill-posedness and the lack of large-scale supervised datasets. Deep Equilibrium (DEQ) models have been used successfully but typically require supervised pairs \((\mathbf{x},\mathbf{y})\). In many practical settings, only measurements \(\mathbf{y}\) are available. We introduce HyDRA (Hybrid Denoising Regularization Adaptation), a measurement-only framework for DEQ training that combines measurement consistency with an adaptive denoising regularization term, together with a data-driven early stopping criterion. Experiments on sparse-view CT demonstrate competitive reconstruction quality and fast inference. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_01228 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | HyDRA: Hybrid Denoising Regularization for Measurement-Only DEQ Training Haltmeier, Markus Neumann, Lukas Gruber, Nadja Schwab, Johannes Hwang, Gyeongha Computer Vision and Pattern Recognition Numerical Analysis Solving image reconstruction problems of the form \(\mathbf{A} \mathbf{x} = \mathbf{y}\) remains challenging due to ill-posedness and the lack of large-scale supervised datasets. Deep Equilibrium (DEQ) models have been used successfully but typically require supervised pairs \((\mathbf{x},\mathbf{y})\). In many practical settings, only measurements \(\mathbf{y}\) are available. We introduce HyDRA (Hybrid Denoising Regularization Adaptation), a measurement-only framework for DEQ training that combines measurement consistency with an adaptive denoising regularization term, together with a data-driven early stopping criterion. Experiments on sparse-view CT demonstrate competitive reconstruction quality and fast inference. |
| title | HyDRA: Hybrid Denoising Regularization for Measurement-Only DEQ Training |
| topic | Computer Vision and Pattern Recognition Numerical Analysis |
| url | https://arxiv.org/abs/2601.01228 |