用无语义的程序化3D模型训练，效果竟不输有语义的模型。
Semantic-Free Procedural 3D Shapes Are Surprisingly Good Teachers
- 用简单几何体和变换自动生成3D形状来训练表示
- 在多个下游任务中性能媲美语义模型，如分类、分割
- 揭示当前3D自监督学习不依赖语义信息
自监督学习为从无标签点云中获取可迁移的3D表征提供了新路径。与广泛可用的2D图像不同，3D资产获取需专业技能或扫描设备，难以规模化且存在版权问题。为此，我们提出从程序化3D程序中学习3D表征，这些程序通过简单3D基本体和变换自动生成3D形状。令人惊讶的是，尽管缺乏语义内容，从程序生成的3D形状中学习的表征在多种下游任务（如形状分类、部件分割、掩码点云补全、场景语义与实例分割）上表现与基于可识别语义模型（如飞机）的先进表征相当。我们详细分析了优质3D程序的特征。大量实验进一步表明，当前点云上的3D自监督学习方法并不依赖3D形状的语义，揭示了所学3D表征的本质。
原文摘要 · Abstract (English)
Self-supervised learning has emerged as a promising approach for acquiring transferable 3D representations from unlabeled 3D point clouds. Unlike 2D images, which are widely accessible, acquiring 3D assets requires specialized expertise or professional 3D scanning equipment, making it difficult to scale and raising copyright concerns. To address these challenges, we propose learning 3D representations from procedural 3D programs that automatically generate 3D shapes using simple 3D primitives and augmentations. Remarkably, despite lacking semantic content, the 3D representations learned from the procedurally generated 3D shapes perform on par with state-of-the-art representations learned from semantically recognizable 3D models (e.g., airplanes) across various downstream 3D tasks, such as shape classification, part segmentation, masked point cloud completion, and both scene semantic and instance segmentation. We provide a detailed analysis on factors that make a good 3D procedural programs. Extensive experiments further suggest that current 3D self-supervised learning methods on point clouds do not rely on semantics of 3D shapes, shedding light on the nature of 3D representations learned.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。