NeRD: Neural field-based Demosaicking

0575759 - ÚTIA 2024 RIV US eng C - Conference Paper (international conference)
Kerepecký, Tomáš - Šroubek, Filip - Novozámský, Adam - Flusser, Jan
NeRD: Neural field-based Demosaicking.
Proceedings of the 2023 IEEE International Conference on Image Processing (ICIP). Piscataway: IEEE, 2023, s. 1735-1739. ISBN 978-1-7281-9835-4.
[IEEE International Conference on Image Processing 2023 (ICIP 2023). Kuala Lumpur (MY), 08.10.2023-11.10.2023]
R&D Projects: GA ČR GA21-03921S
Grant - others:AV ČR(CZ) StrategieAV21/1
Institutional support: RVO:67985556
Keywords : Demosaicking * neural field * implicit neural representation
OECD category: Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
http://library.utia.cas.cz/separaty/2023/ZOI/kerepecky-0575759.pdf

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.
Permanent Link: https://hdl.handle.net/11104/0345842