Neural Networks for Implicit Representations of 3D Scenes

• Luiz Schirmer PUC-Rio
• Guilherme Schardong PUC-Rio
• Vinícius da Silva PUC-Rio
• Hélio Lopes PUC-Rio
• Tiago Novello IMPA
• Daniel Yukimura IMPA
• Thales Magalhaes IMPA
• Hallison Paz IMPA
• Luiz Velho IMPA

Resumo

This survey presents methods that use neural networks for implicit representations of 3D geometry — neural implicit functions. We explore the different aspects of neural implicit functions for shape modeling and synthesis. We aim to provide a theoretical analysis of 3D shape reconstruction using deep neural networks and introduce a discussion between researchers interested in this research field.

Palavras-chave: Geometry, Deep learning, Three-dimensional displays, Shape, Neural networks, Image reconstruction, Neural Networks, Signal Distance Functions, Implicit Representations