PORTO @ 
Archivio Istituzionale della Ricerca
IRIS è la soluzione IT che facilita la raccolta e la gestione dei dati relativi alle attività e ai prodotti della ricerca. Fornisce a ricercatori, amministratori e valutatori gli strumenti per monitorare i risultati della ricerca, aumentarne la visibilità e allocare in modo efficace le risorse disponibili.
EnglishColorization of near-infrared (NIR) images is a challenging problem due to the different material properties at the infared wavelenghts, thus reducing the correlation with visible images. In this paper, we study how graph-convolutional neural networks allow exploiting a more powerful inductive bias than standard CNNs, in the form of non-local self-similiarity. Its impact is evaluated by showing how training with mean squared error only as loss leads to poor results with a standard CNN, while the graph-convolutional network produces significantly sharper and more realistic colorizations.
NIR image colorization with graph-convolutional neural networks / Valsesia, D.; Fracastoro, G.; Magli, E.. - (2020), pp. 451-454. ((Intervento presentato al convegno 2020 IEEE International Conference on Visual Communications and Image Processing, VCIP 2020 tenutosi a chn nel 2020.
Scheda prodotto non validato
Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo
| Titolo: | NIR image colorization with graph-convolutional neural networks | |
| Autori: | ||
| Data di pubblicazione: | 2020 | |
| Abstract: | Colorization of near-infrared (NIR) images is a challenging problem due to the different material... properties at the infared wavelenghts, thus reducing the correlation with visible images. In this paper, we study how graph-convolutional neural networks allow exploiting a more powerful inductive bias than standard CNNs, in the form of non-local self-similiarity. Its impact is evaluated by showing how training with mean squared error only as loss leads to poor results with a standard CNN, while the graph-convolutional network produces significantly sharper and more realistic colorizations. | |
| ISBN: | 978-1-7281-8068-7 | |
| Appare nelle tipologie: | 4.1 Contributo in Atti di convegno |
File in questo prodotto:
| File | Descrizione | Tipologia | Licenza | |
|---|---|---|---|---|
| NIR_colorization_author.pdf | 2. Post-print / Author's Accepted Manuscript | PUBBLICO - Tutti i diritti riservati | Visibile a tuttiVisualizza/Apri | |
| 09301839.pdf | 2a Post-print versione editoriale / Version of Record | Non Pubblico - Accesso privato/ristretto | Administrator Richiedi una copia |
http://hdl.handle.net/11583/2879993
Copyright © 2021