Spline Positional Encoding for Learning 3D Implicit Signed Distance Fields

Peng-Shuai Wang 1    Yang Liu 1    Yu-Qi Yang 21    Xin Tong 1
1 Microsoft Research Asia    2 Tsinghua University   
International Joint Conferences on Artificial Intelligence (IJCAI), 2021


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.

Paper [PDF]

Slides [PPTX]

Code   [Github]

Peng-Shuai Wang, Yang Liu, Yu-Qi Yang, and Xin Tong. 2021. Unsupervised 3D Learning for Shape Analysis via Multiresolution Instance Discrimination Analysis. International Joint Conferences on Artificial Intelligence (IJCAI), 2021.