Neural knitworks : patched neural implicit representation networks
Czerkawski, Mikolaj and Cardona, Javier and Atkinson, Robert and Michie, Craig and Andonovic, Ivan and Clemente, Carmine and Tachtatzis, Christos (2024) Neural knitworks : patched neural implicit representation networks. Pattern Recognition, 151. 110378. ISSN 0031-3203 (https://doi.org/10.1016/j.patcog.2024.110378)
Preview |
Text.
Filename: Czerkawski-etal-PR-2024-Neural-knitworks-patched-neural-implicit-representation-networks.pdf
Final Published Version License: Download (3MB)| Preview |
Abstract
Optimizing images as output of a neural network has been shown to introduce a powerful prior for image inverse tasks, capable of producing solutions of reasonable quality in a fully internal learning context, where no external datasets are involved. Two potential technical approaches involve fitting a coordinate-based Multilayer Perceptron (MLP), or a Convolutional Neural Network to produce the result image as output. The aim of this work is to evaluate the two counterparts, as well as a new framework proposed here, named Neural Knitwork, which maps pixel coordinates to local texture patches rather than singular pixel values. The utility of the proposed technique is demonstrated on the tasks of image inpainting, super-resolution, and denoising. It is shown that the Neural Knitwork can outperform the standard coordinate-based MLP baseline for the tasks of inpainting and denoising, and perform comparably for the super-resolution task.
ORCID iDs
Czerkawski, Mikolaj ORCID: https://orcid.org/0000-0002-0927-0416, Cardona, Javier ORCID: https://orcid.org/0000-0002-9284-1899, Atkinson, Robert ORCID: https://orcid.org/0000-0002-6206-2229, Michie, Craig ORCID: https://orcid.org/0000-0001-5132-4572, Andonovic, Ivan ORCID: https://orcid.org/0000-0001-9093-5245, Clemente, Carmine ORCID: https://orcid.org/0000-0002-6665-693X and Tachtatzis, Christos ORCID: https://orcid.org/0000-0001-9150-6805;-
-
Item type: Article ID code: 88266 Dates: DateEvent31 July 2024Published4 March 2024Published Online25 February 2024Accepted24 August 2022SubmittedSubjects: Science > Mathematics > Electronic computers. Computer science Department: Faculty of Engineering > Electronic and Electrical Engineering
Faculty of Engineering > Chemical and Process Engineering
Strategic Research Themes > Measurement Science and Enabling Technologies
Strategic Research Themes > Ocean, Air and SpaceDepositing user: Pure Administrator Date deposited: 27 Feb 2024 12:23 Last modified: 11 Nov 2024 14:14 URI: https://strathprints.strath.ac.uk/id/eprint/88266