Explicit Neural Surfaces: Learning Continuous Geometry With Deformation Fields

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

We introduce Explicit Neural Surfaces (ENS), an efficient smooth surface representation that directly encodes topology with a deformation field from a known base domain. We apply this representation to reconstruct explicit surfaces from multiple views, where we use a series of neural deformation fields to progressively transform the base domain into a target shape. By using meshes as discrete surface proxies, we train the deformation fields through efficient differentiable rasterization. Using a fixed base domain allows us to have Laplace-Beltrami eigenfunctions as an intrinsic positional encoding alongside standard extrinsic Fourier features, with which our approach can capture fine surface details. Compared to implicit surfaces, ENS trains faster and has several orders of magnitude faster inference times. The explicit nature of our approach also allows higher-quality mesh extraction whilst maintaining competitive surface reconstruction performance and real-time capabilities.
Original languageEnglish
Title of host publicationNeurIPS 2023 Workshop on Symmetry and Geometry in Neural Representations, 2023.
PublisherPMLR
Pages1-22
Number of pages22
Publication statusAccepted/In press - 28 Oct 2023
Event2nd NeurIPS Workshop on Symmetry and Geometry in Neural Representations - New Orleans, United States
Duration: 16 Dec 2023 → …
Conference number: 2
https://www.neurreps.org/about

Publication series

NameProceedings of Machine Learning Research
PublisherPMLR
ISSN (Electronic)2640-3498

Workshop

Workshop2nd NeurIPS Workshop on Symmetry and Geometry in Neural Representations
Abbreviated titleNeurReps 2023
Country/TerritoryUnited States
CityNew Orleans
Period16/12/23 → …
Internet address

Keywords / Materials (for Non-textual outputs)

  • cs.CV
  • cs.GR
  • I.4.5; I.2.10; I.3.5

Fingerprint

Dive into the research topics of 'Explicit Neural Surfaces: Learning Continuous Geometry With Deformation Fields'. Together they form a unique fingerprint.

Cite this