mlsanityData to 7 Oct 2026

Point-Voxel Adaptive Feature Abstraction for Robust Point Cloud Classification

arXiv 2210.15514 ↗First posted 27 Oct 2022cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

Great progress has been made in point cloud classification with learning-based methods. However, complex scene and sensor inaccuracy in real-world application make point cloud data suffer from corruptions, such as occlusion, noise and outliers. In this work, we propose Point-Voxel based Adaptive (PV-Ada) feature abstraction for robust point cloud classification under various corruptions. Specifically, the proposed framework iteratively voxelize the point cloud and extract point-voxel feature with shared local encoding and Transformer. Then, adaptive max-pooling is proposed to robustly aggregate the point cloud feature for classification. Experiments on ModelNet-C dataset demonstrate that PV-Ada outperforms the state-of-the-art methods. In particular, we rank the 2nd place in ModelNet-C classification track of PointCloud-C Challenge 2022, with Overall Accuracy (OA) being 0.865. Code will be available at https://github.com/zhulf0804/PV-Ada.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 26 of its 29 references that are in the map. First posted on arXiv 27 Oct 2022.

Builds on

26 of 29 references.

References · 26

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  4. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  5. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  6. 2020Point Transformercited by 1,462
  7. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  8. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,201
  9. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 890
  10. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  11. 2020PCT: Point cloud transformercited by 730
  12. 2022Masked Autoencoders for Point Cloud Self-supervised Learningcited by 456
14 more
  1. 2022Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Frameworkcited by 376
  2. 2019Point-Voxel CNN for Efficient 3D Deep Learningcited by 343
  3. 2021PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detectioncited by 232
  4. 2022Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Cloudscited by 131
  5. 2022Benchmarking Robustness of 3D Point Cloud Recognition Against Common Corruptionscited by 78
  6. 2020Learning Geometry-Disentangled Representation for Complementary Understanding of 3D Object Point Cloudcited by 71
  7. 2022Benchmarking and Analyzing Point Cloud Classification under Corruptionscited by 70
  8. 2021Regularization Strategy for Point Cloud via Rigidly Mixed Samplecited by 59
  9. 2021Point Cloud Augmentation with Weighted Local Transformationscited by 39
  10. 2021From Voxel to Point: IoU-guided 3D Object Detection for Point Cloud with Voxel-to-Point Decodercited by 23
  11. 2022PVNAS: 3D Neural Architecture Search with Point-Voxel Convolutioncited by 16
  12. 2022PointDP: Diffusion-driven Purification against Adversarial Attacks on 3D Point Cloud Recognitioncited by 16
  13. 20223DeformRS: Certifying Spatial Deformations on Point Cloudscited by 10
  14. 2022PV-RCNN++: Semantical Point-Voxel Feature Interaction for 3D Object Detectioncited by 3

Built on by

Cited by year

Citing papers per year: 2023: 1.

1 paper.

  1. 2023Robo3D: Towards Robust and Reliable 3D Perception against Corruptionscited by 128