arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2507.04801cs.CV
收藏

PointGAC: 用于掩码点云建模的几何感知码本

PointGAC: Geometric-Aware Codebook for Masked Point Cloud Modeling

Jiangxi University of Finance and Economics(江西财经大学);Shenzhen University(深圳大学);University of Technology Sydney(悉尼科技大学);Fondazione Bruno Kessler(布鲁诺·凯斯勒基金会)

Abiao Li, Chenlei Lv, Yuming Fang, Yifan Zuo, Jian Zhang, Guofeng Mei

AI总结:

PointGAC提出基于几何感知码本的聚类式掩码点云建模方法,通过在线码本引导师生框架对齐特征分布,学习泛化表示,实验验证其有效性。

摘要:

大多数掩码点云建模(MPM)方法遵循回归范式来重建掩码区域的坐标或特征。然而,这些方法往往过度约束模型学习掩码区域的细节,导致无法捕获泛化特征。为解决这一局限,我们提出了一种新颖的基于聚类的MPM方法——PointGAC,旨在对齐掩码区域的特征分布。具体而言,该方法采用在线码本引导的师生框架。首先,提出一种几何感知分区策略来提取初始块。然后,教师模型基于完整块提取的特征,通过在线k均值更新码本。该过程促使码本向量成为聚类中心。随后,将未掩码特征分配至对应的聚类中心,学生模型对齐重建掩码特征的分配。该策略聚焦于识别掩码特征所属的聚类中心,使模型能够学习更泛化的特征表示。得益于所提出的码本维护机制,码本向量被主动更新,进一步提高了语义特征学习的效率。实验验证了该方法在各种下游任务上的有效性。代码可在 https://github.com/LAB123-tech/PointGAC 获取。

英文摘要:

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

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑