Upsampling Improvement for Overfitted Neural Coding

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Philippe, Pierrick, Ladune, Théo, Clare, Gordon, Henry, Félix, Blard, Théophile, Leguay, Thomas
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912136931835904
author Philippe, Pierrick
Ladune, Théo
Clare, Gordon
Henry, Félix
Blard, Théophile
Leguay, Thomas
author_facet Philippe, Pierrick
Ladune, Théo
Clare, Gordon
Henry, Félix
Blard, Théophile
Leguay, Thomas
contents Neural image compression, based on auto-encoders and overfitted representations, relies on a latent representation of the coded signal. This representation needs to be compact and uses low resolution feature maps. In the decoding process, those latents are upsampled and filtered using stacks of convolution filters and non linear elements to recover the decoded image. Therefore, the upsampling process is crucial in the design of a neural coding scheme and is of particular importance for overfitted codecs where the network parameters, including the upsampling filters, are part of the representation. This paper addresses the improvement of the upsampling process in order to reduce its complexity and limit the number of parameters. A new upsampling structure is presented whose improvements are illustrated within the Cool-Chic overfitted image coding framework. The proposed approach offers a rate reduction of 4.7%. The code is provided.
format Preprint
id arxiv_https___arxiv_org_abs_2411_19249
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Upsampling Improvement for Overfitted Neural Coding
Philippe, Pierrick
Ladune, Théo
Clare, Gordon
Henry, Félix
Blard, Théophile
Leguay, Thomas
Image and Video Processing
Neural image compression, based on auto-encoders and overfitted representations, relies on a latent representation of the coded signal. This representation needs to be compact and uses low resolution feature maps. In the decoding process, those latents are upsampled and filtered using stacks of convolution filters and non linear elements to recover the decoded image. Therefore, the upsampling process is crucial in the design of a neural coding scheme and is of particular importance for overfitted codecs where the network parameters, including the upsampling filters, are part of the representation. This paper addresses the improvement of the upsampling process in order to reduce its complexity and limit the number of parameters. A new upsampling structure is presented whose improvements are illustrated within the Cool-Chic overfitted image coding framework. The proposed approach offers a rate reduction of 4.7%. The code is provided.
title Upsampling Improvement for Overfitted Neural Coding
topic Image and Video Processing
url https://arxiv.org/abs/2411.19249