Deploying and processing neural representations of signals

De Luigi, Luca (2023) Deploying and processing neural representations of signals, [Dissertation thesis], Alma Mater Studiorum Università di Bologna. Dottorato di ricerca in Computer science and engineering, 35 Ciclo. DOI 10.48676/unibo/amsdottorato/10846.
Documenti full-text disponibili:
[img] Documento PDF (English) - Richiede un lettore di PDF come Xpdf o Adobe Acrobat Reader
Disponibile con Licenza: Creative Commons Attribution Non-commercial ShareAlike 4.0 (CC BY-NC-SA 4.0) .
Download (65MB)


Neural representations (NR) have emerged in the last few years as a powerful tool to represent signals from several domains, such as images, 3D shapes, or audio. Indeed, deep neural networks have been shown capable of approximating continuous functions that describe a given signal with theoretical infinite resolution. This finding allows obtaining representations whose memory footprint is fixed and decoupled from the resolution at which the underlying signal can be sampled, something that is not possible with traditional discrete representations, e.g., grids of pixels for images or voxels for 3D shapes. During the last two years, many techniques have been proposed to improve the capability of NR to approximate high-frequency details and to make the optimization procedures required to obtain NR less demanding both in terms of time and data requirements, motivating many researchers to deploy NR as the main form of data representation for complex pipelines. Following this line of research, we first show that NR can approximate precisely Unsigned Distance Functions, providing an effective way to represent garments that feature open 3D surfaces and unknown topology. Then, we present a pipeline to obtain in a few minutes a compact Neural Twin® for a given object, by exploiting the recent advances in modeling neural radiance fields. Furthermore, we move a step in the direction of adopting NR as a standalone representation, by considering the possibility of performing downstream tasks by processing directly the NR weights. We first show that deep neural networks can be compressed into compact latent codes. Then, we show how this technique can be exploited to perform deep learning on implicit neural representations (INR) of 3D shapes, by only looking at the weights of the networks.

Tipologia del documento
Tesi di dottorato
De Luigi, Luca
Dottorato di ricerca
Settore disciplinare
Settore concorsuale
Parole chiave
Computer Vision, Deep Learning, Neural Representations, Neural Fields, Representation Learning, Implicit Neural Representations
Data di discussione
5 Luglio 2023

Altri metadati

Statistica sui download

Gestione del documento: Visualizza la tesi