RECORD
Learning to Jointly Deblur, Demosaick and Denoise Raw Images
Image and Video Processing · Submitted 13 Apr 2021
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim We demonstrate the effectiveness of this model over two-stage approaches stacking demosaicking and deblurring modules on quantitive benchmarks.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
We address the problem of non-blind deblurring and demosaicking of noisy raw images. We adapt an existing learning-based approach to RGB image deblurring to handle raw images by introducing a new interpretable module that jointly demosaicks and deblurs them. We train this model on RGB images converted into raw ones following a realistic invertible camera pipeline. We demonstrate the effectiveness of this model over two-stage approaches stacking demosaicking and deblurring modules on quantitive benchmarks. We also apply our approach to remove a camera's inherent blur (its color-dependent point-spread function) from real images, in essence deblurring sharp images.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | We address the problem of non-blind deblurring and demosaicking of noisy raw images. | background 0.94 | 0.38 | 0.05 | asserted 0.71 |
| s1 | We adapt an existing learning-based approach to RGB image deblurring to handle raw images by introducing a new interpretable module that jointly demosaicks and deblurs them. | method 0.56 | 0.92 | 0.10 | asserted 1.00 |
| s2 | We train this model on RGB images converted into raw ones following a realistic invertible camera pipeline. | method 1.00 | 0.94 | 0.03 | asserted 0.99 |
| s3 | We demonstrate the effectiveness of this model over two-stage approaches stacking demosaicking and deblurring modules on quantitive benchmarks. | result 0.99 | 0.96 | 0.60 | asserted 1.00 |
| s4 | We also apply our approach to remove a camera's inherent blur (its color-dependent point-spread function) from real images, in essence deblurring sharp images. | contribution 0.76 | 0.94 | 0.12 | asserted 0.99 |
What was examined, and what was not
- arXiv listing abstract v1
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
We address the problem of non-blind deblurring and demosaicking of noisy raw images. We adapt an existing learning-based approach to RGB image deblurring to handle raw images by introducing a new interpretable module that jointly demosaicks and deblurs them. We train this model on RGB images converted into raw ones following a realistic invertible camera pipeline. We demonstrate the effectiveness of this model over two-stage approaches stacking demosaicking and deblurring modules on quantitive benchmarks. We also apply our approach to remove a camera's inherent blur (its color-dependent point-spread function) from real images, in essence deblurring sharp images.
Human review
How the literature uses it
What this paper does with the arXiv papers it cites
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.