How to Train Your (Neural) Dragon

  • Luiz Schirmer Unisinos
  • Tiago Novello IMPA
  • Vinícius da Silva PUC-Rio
  • Guilherme Schardong U Coimbra
  • Hélio Lopes PUC-Rio
  • Luiz Velho IMPA

Resumo


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.
Palavras-chave: neural fields, differential geometry
Publicado
06/11/2023
SCHIRMER, Luiz; NOVELLO, Tiago; SILVA, Vinícius da; SCHARDONG, Guilherme; LOPES, Hélio; VELHO, Luiz. How to Train Your (Neural) Dragon. In: CONFERENCE ON GRAPHICS, PATTERNS AND IMAGES (SIBGRAPI), 36. , 2023, Rio Grande/RS. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2023 . p. 264-269.