Spline Positional Encoding for Learning 3D Implicit Signed Distance Fields

Spline Positional Encoding for Learning 3D Implicit Signed Distance Fields

Peng-Shuai Wang, Yang Liu, Yu-Qi Yang, Xin Tong

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence
Main Track. Pages 1091-1097. https://doi.org/10.24963/ijcai.2021/151

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, which help 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 and 3D shape space learning from input point clouds. The efficacy of our approach extended to image reconstruction is also demonstrated and evaluated.
Keywords:
Computer Vision: 2D and 3D Computer Vision