Downloads · 30 days
0
unrolled_unet_demosaicing
danaroth/unrolled_unet_demosaicing
unrolled_unet_demosaicing is a machine learning model from danaroth. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as cc-by-nc-4.0.
Series of weights recovered by training the ligthning torch model UnrolledSystem implemented in: (Unrolled demosaicking)[https://github.com/mattmull42/unrolleddemosaicking]
Access
Public
Updated Jun 6, 2024
Repo size
389 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.ckpt389 MB · 100%
At a glance
- License
- cc-by-nc-4.0
- Access
- Public
- Created
- Jun 6, 2024
- Updated
- Jun 6, 2024
- SHA
- 595182c3
Model card
From the Hugging Face model README
Description
Series of weights recovered by training the ligthning torch model
UnrolledSystem implemented in:
(Unrolled demosaicking)[https://github.com/mattmull42/unrolled_demosaicking]
The network was trained over 15 color filter array patterns:
bayerbinningchakrabartigindelehamiltonhondahonda2kaizukodakluoquad_bayerrandomsparse_3wang
The network is based on U-NET, unrolled over 4 stages, and plugged into an ADMM solver. The network is trained over 300 natural images, cut into patches of size 64 x 64.
The three versions given in this repository are:
4: Baseline weights.4B: Variant with different training set.4V: Introduces geometric transformations on the patterns.
Citation
If you use this dataset, please cite:
@InProceedings{muller_eusipco_2024,
author = {Muller, Matthieu and Picone, Daniele and Dalla Mura, Mauro and Ulfarsson, Magnus Orn},
booktitle = {European Signal Processing Conference ({EUSIPCO})},
title = {Pattern-invariant unrolling for robust demosaicking},
year = {2024},
}
- License
- cc-by-nc-4.0
- Created
- Jun 6, 2024
- Updated
- Jun 6, 2024