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

• URL: http://arxiv.org/abs/2509.17207v1
• Date: Sun, 21 Sep 2025 19:25:25 GMT
• Title: Point-RTD: Replaced Token Denoising for Pretraining Transformer Models on Point Clouds
• Abstract summary: We introduce Point-RTD (Replaced Token Denoising), a novel pretraining strategy designed to improve token robustness.<n>On the ShapeNet dataset, Point-RTD reduces reconstruction error by over 93% compared to PointMAE, and achieves more than 14x lower Chamfer Distance.
• Score: 3.0232213779552803
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Point-Selection Fine-Tuning Framework for Robust Point Cloud Classification [13.13510696965873]
  PSFT is a point-selection fine-tuning framework that improves robustness while remaining parameter-efficient.<n>We show that PSFT consistently reduces corruption error on Model-C and ModelNet40-C across all tested 3D pre-trained backbones.
  arXiv  Detail & Related papers  (2026-07-22T03:27:18Z)
• Adaptive Point-Prompt Tuning: Fine-Tuning Heterogeneous Foundation Models for 3D Point Cloud Analysis [51.37795317716487]
  We propose the Adaptive Point-Prompt Tuning (APPT) method, which fine-tunes pre-trained models with a modest number of parameters.<n>We convert raw point clouds into point embeddings by aggregating local geometry to capture spatial features followed by linear layers.<n>To calibrate self-attention across source domains of any modality to 3D, we introduce a prompt generator that shares weights with the point embedding module.
  arXiv  Detail & Related papers  (2025-08-30T06:02:21Z)
• Taming Anomalies with Down-Up Sampling Networks: Group Center Preserving Reconstruction for 3D Anomaly Detection [59.822737536103155]
  A Down-Up Sampling Network (DUS-Net) is proposed to reconstruct high-precision point clouds for 3D anomaly detection by preserving the group center geometric structure.<n>The proposed method achieves state-of-the-art (SOTA) performance with an Object-level AUROC of 79.9% and 79.5%, and a Point-level AUROC of 71.2% and 84.7% on the Real3D-AD and Anomaly-ShapeNet datasets.
  arXiv  Detail & Related papers  (2025-07-05T05:05:36Z)
• Efficient Point Transformer with Dynamic Token Aggregating for LiDAR Point Cloud Processing [19.73918716354272]
  LiDAR point cloud processing and analysis have made great progress due to the development of 3D Transformers.<n>Existing 3D Transformer methods usually are computationally expensive and inefficient due to their huge and redundant attention maps.<n>We propose an efficient point TransFormer with Dynamic Token Aggregating (DTA-Former) for point cloud representation and processing.
  arXiv  Detail & Related papers  (2024-05-23T20:50:50Z)
• StarNet: Style-Aware 3D Point Cloud Generation [82.30389817015877]
  StarNet is able to reconstruct and generate high-fidelity and even 3D point clouds using a mapping network. Our framework achieves comparable state-of-the-art performance on various metrics in the point cloud reconstruction and generation tasks.
  arXiv  Detail & Related papers  (2023-03-28T08:21:44Z)
• From Environmental Sound Representation to Robustness of 2D CNN Models Against Adversarial Attacks [82.21746840893658]
  This paper investigates the impact of different standard environmental sound representations (spectrograms) on the recognition performance and adversarial attack robustness of a victim residual convolutional neural network. We show that while the ResNet-18 model trained on DWT spectrograms achieves a high recognition accuracy, attacking this model is relatively more costly for the adversary.
  arXiv  Detail & Related papers  (2022-04-14T15:14:08Z)
• Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling [104.82953953453503]
  We present Point-BERT, a new paradigm for learning Transformers to generalize the concept of BERT to 3D point cloud. Experiments demonstrate that the proposed BERT-style pre-training strategy significantly improves the performance of standard point cloud Transformers.
  arXiv  Detail & Related papers  (2021-11-29T18:59:03Z)
• CpT: Convolutional Point Transformer for 3D Point Cloud Processing [10.389972581905]
  We present CpT: Convolutional point Transformer - a novel deep learning architecture for dealing with the unstructured nature of 3D point cloud data. CpT is an improvement over existing attention-based Convolutions Neural Networks as well as previous 3D point cloud processing transformers. Our model can serve as an effective backbone for various point cloud processing tasks when compared to the existing state-of-the-art approaches.
  arXiv  Detail & Related papers  (2021-11-21T17:45:55Z)
• TENT: Efficient Quantization of Neural Networks on the tiny Edge with Tapered FixEd PoiNT [3.6048665052465663]
  We propose a new low-precision framework, TENT, to leverage the benefits of a tapered fixed-point numerical format in TinyML models. We introduce a tapered fixed-point quantization algorithm that matches the numerical format's dynamic range and distribution to that of the deep neural network model's parameter distribution at each layer. Results show that the accuracy on classification tasks improves up to 31 % with an energy overhead of 17-30 % as compared to fixed-point, for ConvNet and ResNet-18 models.
  arXiv  Detail & Related papers  (2021-04-06T01:54:32Z)
• Deep-3DAligner: Unsupervised 3D Point Set Registration Network With Optimizable Latent Vector [15.900382629390297]
  We propose to develop a novel model that integrates the optimization to learning, aiming to address the technical challenges in 3D registration. In addition to the deep transformation decoding network, our framework introduce an optimizable deep underlineSpatial underlineCorrelation underlineRepresentation.
  arXiv  Detail & Related papers  (2020-09-29T22:44:38Z)
• From Sound Representation to Model Robustness [82.21746840893658]
  We investigate the impact of different standard environmental sound representations (spectrograms) on the recognition performance and adversarial attack robustness of a victim residual convolutional neural network. Averaged over various experiments on three environmental sound datasets, we found the ResNet-18 model outperforms other deep learning architectures.
  arXiv  Detail & Related papers  (2020-07-27T17:30:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.