FILTR：从预训练 3D 模型中提取拓扑特征
FILTR: Extracting Topological Features from Pretrained 3D Models
把持久图生成建模为集合预测任务，用 Transformer 解码器从冻结的 3D 点云编码器特征中前馈预测拓扑描述子，为形状分析提供了一条无需逐样本计算持续同调的快速路径，也提示可用拓扑监督来探测预训练编码器保留的全局结构信息。
原文依据 FILTR adapts a transformer decoder to treat diagram generation as a set prediction task.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论近期 3D 点云编码器预训练（如 Point-BERT、Point-MAE）的进展催生了强大的模型，其能力通常在几何或语义任务上评估。与此同时，拓扑描述子已被证明能够为形状的多尺度结构提供有信息量的概括。本文提出一个问题：能否从 3D 编码器产生的特征中导出拓扑信息。为回答该问题，我们首先引入 DONUT，一个拓扑复杂度受控的合成基准，并提出 FILTR（Filtration Transformer），一个可直接从冻结编码器预测持久图的可学习框架。FILTR 改造 Transformer 解码器，将图的生成视为集合预测任务。我们在 DONUT 上的分析表明，现有编码器仅保留有限的全局拓扑信号，但 FILTR 成功利用了这些编码器产生的信息来近似持久图。我们的方法首次实现了通过高效的可学习前馈机制从原始点云中数据驱动地提取持久图。
英文原文摘要 1142 字符
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 of a shape's multiscale structure. In this paper we pose the question whether topological information can be derived from features produced by 3D encoders. To address this question, we first introduce DONUT, a synthetic benchmark with controlled topological complexity, and propose FILTR (Filtration Transformer), a learnable framework to predict persistence diagrams directly from frozen encoders. FILTR adapts a transformer decoder to treat diagram generation as a set prediction task. Our analysis on DONUT reveals that existing encoders retain only limited global topological signals, yet FILTR successfully leverages information produced by these encoders to approximate persistence diagrams. Our approach enables, for the first time, data-driven extraction of persistence diagrams from raw point clouds through an efficient learnable feed-forward mechanism.