mlsanityData to 14 Oct 2026

Point-RTD: Replaced Token Denoising for Pretraining Transformer Models on Point Clouds

arXiv 2509.17207 ↗First posted 21 Sep 2025cs.CV cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Pre-training strategies play a critical role in advancing the performance of transformer-based models for 3D point cloud tasks. In this paper, we introduce Point-RTD (Replaced Token Denoising), a novel pretraining strategy designed to improve token robustness through a corruption-reconstruction framework. Unlike traditional mask-based reconstruction tasks that hide data segments for later prediction, Point-RTD corrupts point cloud tokens and leverages a discriminator-generator architecture for denoising. This shift enables more effective learning of structural priors and significantly enhances model performance and efficiency. On the ShapeNet dataset, Point-RTD reduces reconstruction error by over 93% compared to PointMAE, and achieves more than 14x lower Chamfer Distance on the test set. Our method also converges faster and yields higher classification accuracy on ShapeNet, ModelNet10, and ModelNet40 benchmarks, clearly outperforming the baseline Point-MAE framework in every case.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 25 of its 30 references that are in the map. First posted on arXiv 21 Sep 2025.

Builds on

25 of 30 references.

References · 25

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  4. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  5. 2020Point Transformercited by 1,470
  6. 2020PCT: Point cloud transformercited by 732
  7. 2021Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modelingcited by 653
  8. 2019Deep Learning for 3D Point Clouds: A Surveycited by 558
  9. 2022Masked Autoencoders for Point Cloud Self-supervised Learningcited by 459
  10. 2022Point Transformer V2: Grouped Vector Attention and Partition-based Poolingcited by 388
  11. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
  12. 2021An End-to-End Transformer Model for 3D Object Detectioncited by 329
13 more
  1. 2022Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-trainingcited by 264
  2. 2021Voxel Transformer for 3D Object Detectioncited by 247
  3. 2023Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretrainingcited by 164
  4. 2022Masked Discrimination for Self-Supervised Learning on Point Cloudscited by 155
  5. 2022Learning 3D Representations from 2D Pre-trained Models via Image-to-Point Masked Autoencoderscited by 144
  6. 2024ShapeLLM: Universal 3D Object Understanding for Embodied Interactioncited by 137
  7. 2022Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?cited by 122
  8. 2023PointGPT: Auto-regressively Generative Pre-training from Point Cloudscited by 115
  9. 2022P2P: Tuning Pre-trained Image Models for Point Cloud Analysis with Point-to-Pixel Promptingcited by 74
  10. 2023Towards Compact 3D Representations via Point Feature Enhancement Masked Autoencoderscited by 42
  11. 2022Masked Autoencoders in 3D Point Cloud Representation Learningcited by 30
  12. 2022GanLM: Encoder-Decoder Pre-training with an Auxiliary Discriminatorcited by 20
  13. 2023PointGame: Geometrically and Adaptively Masked Auto-Encoder on Point Cloudscited by 4

Built on by

Not cited yet.