Skip to main content
top

Bibliography

Conference Paper (international conference)

NeRD: Neural field-based Demosaicking

Kerepecký Tomáš, Šroubek Filip, Novozámský Adam, Flusser Jan

: Proceedings of the 2023 IEEE International Conference on Image Processing (ICIP), p. 1735-1739

: IEEE International Conference on Image Processing 2023 (ICIP 2023), (Kuala Lumpur, MY, 20231008)

: GA21-03921S, GA ČR, StrategieAV21/1, AV ČR, ,

: Demosaicking, neural field, implicit neural representation

: 10.1109/ICIP49359.2023.10221948

: http://library.utia.cas.cz/separaty/2023/ZOI/kerepecky-0575759.pdf

(eng): 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.

: JC

: 10201