How to train your (neural) dragon

被引：0

作者：

Schirmer, Luiz ^{[1
]}

Novello, Tiago ^{[2
]}

da Silva, Vinicius ^{[3
]}

Schardong, Guilherme ^{[4
]}

Lopes, Helio ^{[3
]}

Velho, Luiz ^{[2
]}

机构：

[1] Univ Vale Rio dos Sinos, Sao Leopoldo, Brazil

[2] IMPA, Rio De Janeiro, Brazil

[3] Pontificia Univ Catolica Rio de Janeiro, Rio de Janeiro, Brazil

[4] Univ Coimbra, Coimbra, Portugal

来源：

2023 36TH CONFERENCE ON GRAPHICS, PATTERNS AND IMAGES, SIBGRAPI 2023 | 2023年

关键词：

neural fields; differential geometry;

D O I：

10.1109/SIBGRAPI59091.2023.10347177

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

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.

引用

页码：264 / 269

页数：6

共 16 条

[1]

Carr JC, 2001, COMP GRAPH, P67, DOI 10.1145/383259.383266

[2]

Cohen-Steiner D, 2003, P 19 ANN S COMP GEOM, P237, DOI [10.1145/777792.777839, DOI 10.1145/777792.777839]

[3] A Physics-Informed Neural Network Framework for PDEs on 3D Surfaces: Time Independent Problems [J].

Fang, Zhiwei ;

Zhan, Justin .

IEEE ACCESS, 2020, 8 :26328-26335

[4]

Gropp A, 2020, Arxiv, DOI [arXiv:2002.10099, DOI 10.48550/ARXIV.2002.10099]

[5] MeshUDF: Fast and Differentiable Meshing of Unsigned Distance Field Networks [J].

Guillard, Benoit ;

Stella, Federico ;

Fua, Pascal .

COMPUTER VISION - ECCV 2022, PT III, 2022, 13663 :576-592

[6]

Kazhdan M, 2006, PROC 4 EUROGRAPHICS, V7, P1, DOI DOI 10.2312/SGP/SGP06/061-070

[7]

Lapedes A., 1987, LAUR872662

[8]

Meyer N, 2003, VISUALIZATION AND MATHEMATICS III, P35

[9]

Neyshabur B, 2017, Arxiv, DOI arXiv:1709.01953

[10] Exploring differential geometry in neural implicits [J].

Novello, Tiago ;

Schardong, Guilherme ;

Schirmer, Luiz ;

da Silva, Vinicius ;

Lopes, Helio ;

Velho, Luiz .

COMPUTERS & GRAPHICS-UK, 2022, 108 :49-60

← 1 2 →