Spline Positional Encoding for Learning 3D Implicit Signed Distance Fields

TL;DR

This paper introduces Spline Positional Encoding, a new method to improve 3D shape reconstruction and shape space learning from point clouds and images using MLPs.

Contribution

It proposes a novel spline-based positional encoding scheme that enhances the recovery of detailed 3D signed distance fields from unorganized point clouds.

Findings

Outperforms existing positional encoding schemes in 3D shape reconstruction

Effective in shape space learning from point clouds

Demonstrates applicability to image reconstruction

Abstract

Multilayer perceptrons (MLPs) have been successfully used to represent 3D shapes implicitly and compactly, by mapping 3D coordinates to the corresponding signed distance values or occupancy values. In this paper, we propose a novel positional encoding scheme, called Spline Positional Encoding, to map the input coordinates to a high dimensional space before passing them to MLPs, for helping to recover 3D signed distance fields with fine-scale geometric details from unorganized 3D point clouds. We verified the superiority of our approach over other positional encoding schemes on tasks of 3D shape reconstruction from input point clouds and shape space learning. The efficacy of our approach extended to image reconstruction is also demonstrated and evaluated.