mlsanityData to 7 Oct 2026

FILTR: Extracting Topological Features from Pretrained 3D Models

arXiv 2604.22334 ↗First posted 24 Apr 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 45 of its 61 references that are in the map. First posted on arXiv 24 Apr 2026.

Builds on

45 of 61 references.

References · 45

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  4. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  5. 2020End-to-End Object Detection with Transformerscited by 7,384
  6. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  7. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  8. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  9. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  10. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  11. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  12. 2019Similarity of Neural Network Representations Revisitedcited by 1,695
33 more
  1. 2017Deep Setscited by 1,394
  2. 2021Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modelingcited by 647
  3. 2023Point Transformer V3: Simpler, Faster, Strongercited by 579
  4. 2020PointContrast: Unsupervised Pre-training for 3D Point Cloud Understandingcited by 502
  5. 2018ABC: A Big CAD Model Dataset For Geometric Deep Learningcited by 339
  6. 2021An End-to-End Transformer Model for 3D Object Detectioncited by 329
  7. 2022Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-trainingcited by 263
  8. 2022CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understandingcited by 198
  9. 2020Unsupervised Point Cloud Pre-Training via Occlusion Completioncited by 186
  10. 2016Thingi10K: A Dataset of 10,000 3D-Printing Modelscited by 182
  11. 2022Masked Discrimination for Self-Supervised Learning on Point Cloudscited by 155
  12. 2019PersLay: A Neural Network Layer for Persistence Diagrams and New Graph Topological Signaturescited by 125
  13. 2023PointGPT: Auto-regressively Generative Pre-training from Point Cloudscited by 115
  14. 2017Deep Learning with Topological Signaturescited by 113
  15. 2022Surface Representation for Point Cloudscited by 84
  16. 2022Reliability of CKA as a Similarity Measure in Deep Learningcited by 82
  17. 2017Sliced Wasserstein Kernel for Persistence Diagramscited by 77
  18. 2014A Stable Multi-Scale Kernel for Topological Machine Learningcited by 74
  19. 2019Deep Set Prediction Networkscited by 71
  20. 2018Persistence Fisher Kernel: A Riemannian Manifold Kernel for Persistence Diagramscited by 33
  21. 2024Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Cloudcited by 29
  22. 2023Point2Vec for Self-Supervised Representation Learning on Point Cloudscited by 28
  23. 2020GPU-Accelerated Computation of Vietoris-Rips Persistence Barcodescited by 26
  24. 2024PCP-MAE: Learning to Predict Centers for Point Masked Autoencoderscited by 23
  25. 2022RipsNet: a general architecture for fast and robust estimation of the persistent homology of point cloudscited by 20
  26. 2014Subsampling Methods for Persistent Homologycited by 17
  27. 2015Clique topology reveals intrinsic geometric structure in neural correlationscited by 17
  28. 2022Neural Approximation of Graph Topological Featurescited by 16
  29. 2023T-MAE: Temporal Masked Autoencoders for Point Cloud Representation Learningcited by 11
  30. 2024Revisiting Point Cloud Completion: Are We Ready For The Real-World?cited by 4
  31. 2021Fast Approximation of Persistence Diagrams with Guaranteescited by 2
  32. 2024Multiset Transformer: Advancing Representation Learning in Persistence Diagramscited by 2
  33. 2025EuLearn: A 3D database for learning Euler characteristicscited by 1

Built on by

Not cited yet.