PORTALE DELLA DIDATTICA

Ricerca CERCA
  KEYWORD

Image Processing Lab (IPL)

Meta-learning instant neural graphics

Parole chiave DEEP NEURAL NETWORKS

Riferimenti ENRICO MAGLI, DIEGO VALSESIA

Gruppi di ricerca CCNE - COMMUNICATIONS AND COMPUTER NETWORKS ENGINEERING, ICT4SS - ICT FOR SMART SOCIETIES, Image Processing Lab (IPL)

Tipo tesi RESEARCH

Descrizione Instant Neural Graphics Primitives (Instant NGP) [1] have shown great success in solving 3D tasks like view synthesis, surface reconstruction and general signal representation. Despite their speed, they require to solve an optimization problem at test time, which still limits their scalability, and they possess no prior knowledge about the target signals. In this thesis, the candidate will study meta-learning techniques to provide an initialization point with prior knowledge to Instant NGP. This is expected to provide benefits such as accelerated convergence, higher-quality solutions or improve the rate-distortion performance of the representation if used for compression, as suggested by evidence on older implicit representation models [2,3].

[1] Thomas Muller, Alex Evans, Christoph Schied, Alexander Keller, "Instant Neural Graphics Primitives with a Multiresolution Hash Encoding", ACM Transactions on Graphics 2022
[2] Matthew Tancik, Ben Mildenhall, Terrance Wang, Divi Schmidt, Pratul P. Srinivasan, Jonathan T. Barron, and Ren Ng, "Learned initializations for optimizing coordinate-based neural representations", CVPR 2021
[3] Francesca Pistilli, Diego Valsesia, Giulia Fracastoro, Enrico Magli, "Signal Compression via Neural Implicit Representations", ICASSP 2022

Conoscenze richieste The candidate is required to have familiarity with neural networks and pytorch.


Scadenza validita proposta 03/06/2023      PROPONI LA TUA CANDIDATURA




© Politecnico di Torino
Corso Duca degli Abruzzi, 24 - 10129 Torino, ITALY
Contatti