Optimizing 3D Geometry Reconstruction from Implicit Neural Representations

Document Type

Conference Proceeding

Publication Date

1-1-2024

Abstract

Implicit neural representations (INRs) have emerged as a powerful tool in learning 3D geometry, offering unparalleled advantages over conventional representations like mesh-based methods. A common type of INR implicitly encodes a shape's boundary as the zero-level set of the learned continuous function and learns a mapping from a low-dimensional latent space to the space of all possible shapes represented by its signed distance function. However, most INRs struggle to retain high-frequency details, which are crucial for accurate geometric depiction, and they are computationally expensive. To address these limitations, we present a novel approach that both reduces computational expenses and enhances the capture of fine details. Our method integrates periodic activation functions, positional encodings, and normals into the neural network architecture. This integration significantly enhances the model's ability to learn the entire space of 3D shapes while preserving intricate details and sharp features, areas where conventional representations often fall short.

Identifier

105000906436 (Scopus)

ISBN

[9798350374889]

Publication Title

Proceedings - 2024 International Conference on Machine Learning and Applications, ICMLA 2024

External Full Text Location

https://doi.org/10.1109/ICMLA61862.2024.00117

First Page

816

Last Page

821

This document is currently not available here.

Share

COinS