面向点云学习的更多样化、更具挑战性的预训练：基于解耦视图的自监督交叉重建
Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views
AI总结：
针对现有单视图点云自监督预训练多样性不足的问题，提出基于解耦视图的交叉重建范式Point-PQAE，通过裁剪机制生成双视图并设计新型位置编码，在ScanObjectNN数据集上显著超越Point-MAE基线。
摘要：
点云学习，尤其是无需人工标注的自监督式点云学习，因其在众多应用中的潜在实用价值，在视觉与学习领域受到越来越多的关注。现有的大多数点云自监督学习生成式方法，都聚焦于从单个视图内的可见点恢复被掩码的点。研究者意识到双视图预训练范式本质上能引入更高的多样性与方差，因此可能实现更具挑战性、信息量更丰富的预训练。受此启发，本文探索了双视图学习在该领域的潜力。\n本文提出Point-PQAE，这是一种交叉重建生成式范式：先生成两个解耦的点云/视图，再利用其中一个重建另一个。为实现这一目标，本文首次开发了用于点云视图生成的裁剪机制，并进一步提出一种新颖的位置编码，用于表示两个解耦视图之间的3D相对位置。与自重建相比，交叉重建显著提升了预训练的难度，这使得本方法在3D自监督学习中超越了以往的单模态自重建方法。具体而言，在ScanObjectNN的三个变体上采用Mlp-Linear评估协议时，其性能优于自重建基线（Point-MAE）6.5%、7.0%和6.7%。代码可在https://github.com/aHapBean/Point-PQAE获取。
英文摘要：
Point cloud learning, especially in a self-supervised way without manual labels, has gained growing attention in both vision and learning communities due to its potential utility in a wide range of applications. Most existing generative approaches for point cloud self-supervised learning focus on recovering masked points from visible ones within a single view. Recognizing that a two-view pre-training paradigm inherently introduces greater diversity and variance, it may thus enable more challenging and informative pre-training. Inspired by this, we explore the potential of two-view learning in this domain. In this paper, we propose Point-PQAE, a cross-reconstruction generative paradigm that first generates two decoupled point clouds/views and then reconstructs one from the other. To achieve this goal, we develop a crop mechanism for point cloud view generation for the first time and further propose a novel positional encoding to represent the 3D relative position between the two decoupled views. The cross-reconstruction significantly increases the difficulty of pre-training compared to self-reconstruction, which enables our method to surpass previous single-modal self-reconstruction methods in 3D self-supervised learning. Specifically, it outperforms the self-reconstruction baseline (Point-MAE) by 6.5%, 7.0%, and 6.7% in three variants of ScanObjectNN with the Mlp-Linear evaluation protocol. The code is available at https://github.com/aHapBean/Point-PQAE.
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。
