研究人员开发了FILTR，一个旨在从预训练的3D模型中提取拓扑特征的新型框架。该方法将Transformer解码器应用于生成持久性图（persistence diagrams），这些图直接从冻结的编码器中总结形状的多尺度结构。尽管现有的3D编码器显示出有限的全局拓扑信号，FILTR有效地利用其输出来近似这些图，从而实现从原始点云进行数据驱动的提取。 AI
影响 能够从3D点云中进行数据驱动的拓扑特征提取，可能改进计算机视觉中的形状分析和理解。
排序理由 这是一篇介绍从3D模型中提取拓扑特征新方法的学术论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2604.22334v1 Announce Type: new Abstract: Recent advances in pretraining 3D point cloud encoders (e.g., Point-BERT, Point-MAE) have produced powerful models, whose abilities are typically evaluated on geometric or semantic tasks. At the same time, topological descriptors ha…
Recent advances in pretraining 3D point cloud encoders (e.g., Point-BERT, Point-MAE) have produced powerful models, whose abilities are typically evaluated on geometric or semantic tasks. At the same time, topological descriptors have been shown to provide informative summaries o…