GP-Aligner: Unsupervised Non-rigid Groupwise Point Set Registration Based On Optimized Group Latent Descriptor

TL;DR

GP-Aligner is a novel unsupervised method that uses a learnable latent descriptor and neural networks to efficiently align multiple highly deformed 3D point sets without requiring large training datasets.

Contribution

It introduces a model-free, learnable group latent descriptor for non-rigid groupwise registration, avoiding explicit feature encoding networks and large-scale training.

Findings

Achieves superior accuracy over state-of-the-art methods.

Demonstrates high efficiency in aligning many groups of real-world 3D shapes.

Operates in a one-stage optimization without large training data.

Abstract

In this paper, we propose a novel method named GP-Aligner to deal with the problem of non-rigid groupwise point set registration. Compared to previous non-learning approaches, our proposed method gains competitive advantages by leveraging the power of deep neural networks to effectively and efficiently learn to align a large number of highly deformed 3D shapes with superior performance. Unlike most learning-based methods that use an explicit feature encoding network to extract the per-shape features and their correlations, our model leverages a model-free learnable latent descriptor to characterize the group relationship. More specifically, for a given group we first define an optimizable Group Latent Descriptor (GLD) to characterize the gruopwise relationship among a group of point sets. Each GLD is randomly initialized from a Gaussian distribution and then concatenated with the coordinates of each point of the associated point sets in the group. A neural network-based decoder is further constructed to predict the coherent drifts as the desired transformation from input groups of shapes to aligned groups of shapes. During the optimization process, GP-Aligner jointly updates all GLDs and weight parameters of the decoder network towards the minimization of an unsupervised groupwise alignment loss. After optimization, for each group our model coherently drives each point set towards a middle, common position (shape) without specifying one as the target. GP-Aligner does not require large-scale training data for network training and it can directly align groups of point sets in a one-stage optimization process. GP-Aligner shows both accuracy and computational efficiency improvement in comparison with state-of-the-art methods for groupwise point set registration. Moreover, GP-Aligner is shown great efficiency in aligning a large number of groups of real-world 3D shapes.