Unsupervised Partial Point Set Registration via Joint Shape Completion and Registration

TL;DR

This paper introduces an unsupervised method that combines shape completion and registration using shared latent codes, significantly improving partial point set registration performance without requiring ground truth supervision.

Contribution

It proposes a joint shape completion and registration framework with shared latent codes, enhancing registration accuracy for partial shapes without supervision.

Findings

Effective on ModelNet40 dataset

Outperforms existing partial registration methods

Joint optimization benefits shape understanding

Abstract

We propose a self-supervised method for partial point set registration. While recent proposed learning-based methods have achieved impressive registration performance on the full shape observations, these methods mostly suffer from performance degradation when dealing with partial shapes. To bridge the performance gaps between partial point set registration with full point set registration, we proposed to incorporate a shape completion network to benefit the registration process. To achieve this, we design a latent code for each pair of shapes, which can be regarded as a geometric encoding of the target shape. By doing so, our model does need an explicit feature embedding network to learn the feature encodings. More importantly, both our shape completion network and the point set registration network take the shared latent codes as input, which are optimized along with the parameters of two decoder networks in the training process. Therefore, the point set registration process can thus benefit from the joint optimization process of latent codes, which are enforced to represent the information of full shape instead of partial ones. In the inference stage, we fix the network parameter and optimize the latent codes to get the optimal shape completion and registration results. Our proposed method is pure unsupervised and does not need any ground truth supervision. Experiments on the ModelNet40 dataset demonstrate the effectiveness of our model for partial point set registration.