How to Train Your (Neural) Dragon

Neural fields have emerged as a promising framework for representing different types of signals. This tutorial focus on the existing literature and shares practical insights derived from hands-on experimentation with neural fields, specifically in approximating implicit functions of surfaces. Our em...

Full description

Saved in:
Bibliographic Details
Main Authors: Schirmer, Luiz, Novello, Tiago, da Silva, Vinicius, Schardong, Guilherme, Lopes, Helio, Velho, Luiz
Format: Conference Proceeding
Language:English
Subjects:
Data models
differential geometry
Geometry
Graphics
neural fields
Neural networks
Noise measurement
Training
Tutorials
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Neural fields have emerged as a promising framework for representing different types of signals. This tutorial focus on the existing literature and shares practical insights derived from hands-on experimentation with neural fields, specifically in approximating implicit functions of surfaces. Our emphasis lies in strategies leveraging differential geometry concepts to enhance training outcomes and showcase applications within this domain.
ISSN:2377-5416
DOI:10.1109/SIBGRAPI59091.2023.10347177