NeRD: Neural field-based Demosaicking

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985556%3A_____%2F23%3A00575759" target="_blank" >RIV/67985556:_____/23:00575759 - isvavai.cz</a>

Alternative codes found

RIV/68407700:21340/23:00374129

Result on the web

<a href="http://dx.doi.org/10.1109/ICIP49359.2023.10221948" target="_blank" >http://dx.doi.org/10.1109/ICIP49359.2023.10221948</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ICIP49359.2023.10221948" target="_blank" >10.1109/ICIP49359.2023.10221948</a>

Result language

angličtina

Original language name

NeRD: Neural field-based Demosaicking

Original language description

We introduce NeRD, a new demosaicking method for generating full-color images from Bayer patterns. Our approach leverages advancements in neural fields to perform demosaicking by representing an image as a coordinate-based neural network with sine activation functions. The inputs to the network are spatial coordinates and a low-resolution Bayer pattern, while the outputs are the corresponding RGB values. An encoder network, which is a blend of ResNet and U-net, enhances the implicit neural representation of the image to improve its quality and ensure spatial consistency through prior learning. Our experimental results demonstrate that NeRD outperforms traditional and state-of-the-art CNN-based methods and significantly closes the gap to transformer-based methods.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

<a href="/en/project/GA21-03921S" target="_blank" >GA21-03921S: Inverse problems in image processing</a><br>

Continuities

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Publication year

2023

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

Proceedings of the 2023 IEEE International Conference on Image Processing (ICIP)

ISBN

978-1-7281-9835-4

ISSN

—

e-ISSN

—

Number of pages

5

Pages from-to

1735-1739

Publisher name

IEEE

Place of publication

Piscataway

Event location

Kuala Lumpur

Event date

Oct 8, 2023

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—