PointGAC: Geometric-Aware Codebook for Masked Point Cloud Modeling

TL;DR

PointGAC introduces a clustering-based masked point cloud modeling approach that uses an online codebook-guided teacher-student framework to learn more generalized features, improving downstream task performance.

Contribution

It proposes a novel geometry-aware clustering method with an online codebook and teacher-student framework for masked point cloud modeling.

Findings

Effective in capturing generalized features

Improves downstream task performance

Outperforms existing methods

Abstract

Most masked point cloud modeling (MPM) methods follow a regression paradigm to reconstruct the coordinate or feature of masked regions. However, they tend to over-constrain the model to learn the details of the masked region, resulting in failure to capture generalized features. To address this limitation, we propose \textbf{\textit{PointGAC}}, a novel clustering-based MPM method that aims to align the feature distribution of masked regions. Specially, it features an online codebook-guided teacher-student framework. Firstly, it presents a geometry-aware partitioning strategy to extract initial patches. Then, the teacher model updates a codebook via online k-means based on features extracted from the complete patches. This procedure facilitates codebook vectors to become cluster centers. Afterward, we assigns the unmasked features to their corresponding cluster centers, and the student model aligns the assignment for the reconstructed masked features. This strategy focuses on identifying the cluster centers to which the masked features belong, enabling the model to learn more generalized feature representations. Benefiting from a proposed codebook maintenance mechanism, codebook vectors are actively updated, which further increases the efficiency of semantic feature learning. Experiments validate the effectiveness of the proposed method on various downstream tasks. Code is available at https://github.com/LAB123-tech/PointGAC