mlsanityData to 7 Oct 2026

Test-Time Augmentation for 3D Point Cloud Classification and Segmentation

arXiv 2311.13152 ↗First posted 22 Nov 2023cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Data augmentation is a powerful technique to enhance the performance of a deep learning task but has received less attention in 3D deep learning. It is well known that when 3D shapes are sparsely represented with low point density, the performance of the downstream tasks drops significantly. This work explores test-time augmentation (TTA) for 3D point clouds. We are inspired by the recent revolution of learning implicit representation and point cloud upsampling, which can produce high-quality 3D surface reconstruction and proximity-to-surface, respectively. Our idea is to leverage the implicit field reconstruction or point cloud upsampling techniques as a systematic way to augment point cloud data. Mainly, we test both strategies by sampling points from the reconstructed results and using the sampled point cloud as test-time augmented data. We show that both strategies are effective in improving accuracy. We observed that point cloud upsampling for test-time augmentation can lead to more significant performance improvement on downstream tasks such as object classification and segmentation on the ModelNet40, ShapeNet, ScanObjectNN, and SemanticKITTI datasets, especially for sparse point clouds.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 60 of its 82 references that are in the map. First posted on arXiv 22 Nov 2023.

Builds on

60 of 82 references.

References · 60

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  5. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  6. 2014Going Deeper with Convolutionscited by 4,231
  7. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  8. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  9. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  10. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  11. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  12. 20163D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotationcited by 1,471
38 more
  1. 2020Point Transformercited by 1,462
  2. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 972
  3. 2017End-to-end Recovery of Human Shape and Posecited by 883
  4. 2019Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representationscited by 864
  5. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  6. 2020Convolutional Occupancy Networkscited by 760
  7. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 746
  8. 2020Implicit Geometric Regularization for Learning Shapescited by 707
  9. 20163D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstructioncited by 587
  10. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 584
  11. 2016Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modelingcited by 558
  12. 2018AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generationcited by 539
  13. 2019Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Datacited by 532
  14. 2019PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flowscited by 487
  15. 2022PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategiescited by 432
  16. 2017Large-scale Point Cloud Semantic Segmentation with Superpoint Graphscited by 384
  17. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
  18. 2019Point-Voxel CNN for Efficient 3D Deep Learningcited by 343
  19. 2020Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstructioncited by 321
  20. 2018Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networkscited by 278
  21. 2018Generating 3D faces using Convolutional Mesh Autoencoderscited by 267
  22. 2018SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filterscited by 261
  23. 2016Shape Completion using 3D-Encoder-Predictor CNNs and Shape Synthesiscited by 219
  24. 2018PU-Net: Point Cloud Upsampling Networkcited by 208
  25. 2017SEGCloud: Semantic Segmentation of 3D Point Cloudscited by 178
  26. 2020SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentationcited by 170
  27. 2021Deep Parametric Continuous Convolutional Neural Networkscited by 161
  28. 2017Escape from Cells: Deep Kd-Networks for the Recognition of 3D Point Cloud Modelscited by 142
  29. 2017Learning Efficient Point Cloud Generation for Dense 3D Object Reconstructioncited by 133
  30. 2018Show, Attend and Read: A Simple and Strong Baseline for Irregular Text Recognitioncited by 130
  31. 20183DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentationcited by 118
  32. 2019ShellNet: Efficient Point Cloud Convolutional Neural Networks using Concentric Shells Statisticscited by 104
  33. 2020PointMixup: Augmentation for Point Cloudscited by 104
  34. 2019Efficient Learning on Point Clouds with Basis Point Setscited by 101
  35. 2018EC-Net: an Edge-aware Point set Consolidation Networkcited by 84
  36. 2018Recurrent Slice Networks for 3D Segmentation of Point Cloudscited by 82
  37. 2021Point Cloud Upsampling via Disentangled Refinementcited by 74
  38. 2021PointMixer: MLP-Mixer for Point Cloud Understandingcited by 71

50 most cited of 60 All 60 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 0; 2026: 3.

4 papers.

  1. 2026ForestMamba: Sparse Mamba with Geometry-guided Queries for 3D Forest Point Cloud Segmentationcited by 3
  2. 20243D-VirtFusion: Synthetic 3D Data Augmentation through Generative Diffusion Models and Controllable Editingcited by 0
  3. 2026Annotation Free Spacecraft Detection and Segmentation using Vision Language Modelscited by 0
  4. 2026SelectAnyTree: A Promptable Instance Segmentation Model for 3D Forest LiDAR Point Cloudscited by 0