mlsanityData to 7 Oct 2026

Multi-view Structural Convolution Network for Domain-Invariant Point Cloud Recognition of Autonomous Vehicles

arXiv 2501.16289 ↗First posted 27 Jan 2025cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Point cloud representation has recently become a research hotspot in the field of computer vision and has been utilized for autonomous vehicles. However, adapting deep learning networks for point cloud data recognition is challenging due to the variability in datasets and sensor technologies. This variability underscores the necessity for adaptive techniques to maintain accuracy under different conditions. In this paper, we present the Multi-View Structural Convolution Network (MSCN) designed for domain-invariant point cloud recognition. MSCN comprises Structural Convolution Layers (SCL) that extract local context geometric features from point clouds and Structural Aggregation Layers (SAL) that extract and aggregate both local and overall context features from point clouds. Furthermore, MSCN enhances feature robustness by training with unseen domain point clouds generated from the source domain, enabling the model to acquire domain-invariant representations. Extensive cross-domain experiments demonstrate that MSCN achieves an average accuracy of 82.0%, surpassing the strong baseline PointTransformer by 15.8%, confirming its effectiveness under real-world domain shifts. Our code is available at https://github.com/MLMLab/MSCN.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 40 of its 55 references that are in the map. First posted on arXiv 27 Jan 2025.

Builds on

40 of 55 references.

References · 40

  1. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  2. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  3. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  4. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  5. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  6. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  7. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
  8. 2020Point Transformercited by 1,462
  9. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  10. 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
  11. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  12. 2020PCT: Point cloud transformercited by 730
28 more
  1. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 656
  2. 2021Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modelingcited by 647
  3. 2015Multi-view Convolutional Neural Networks for 3D Shape Recognitioncited by 564
  4. 2019Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Datacited by 532
  5. 2018Generalizing to Unseen Domains via Adversarial Data Augmentationcited by 451
  6. 2022PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategiescited by 432
  7. 2022Point Transformer V2: Grouped Vector Attention and Partition-based Poolingcited by 384
  8. 2022Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Frameworkcited by 376
  9. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
  10. 2016OctNet: Learning Deep 3D Representations at High Resolutionscited by 340
  11. 2020Learning to Learn Single Domain Generalizationcited by 295
  12. 2018SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filterscited by 261
  13. 2020PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Samplingcited by 238
  14. 2020Unsupervised Point Cloud Pre-Training via Occlusion Completioncited by 186
  15. 2024PointMamba: A Simple State Space Model for Point Cloud Analysiscited by 166
  16. 2022Masked Discrimination for Self-Supervised Learning on Point Cloudscited by 155
  17. 2020MVTN: Multi-View Transformation Network for 3D Shape Recognitioncited by 140
  18. 2020Rethinking Bias-Variance Trade-off for Generalization of Neural Networkscited by 107
  19. 2019DensePoint: Learning Densely Contextual Representation for Efficient Point Cloud Processingcited by 104
  20. 2021Progressive Domain Expansion Network for Single Domain Generalizationcited by 96
  21. 2022Surface Representation for Point Cloudscited by 84
  22. 2019Open Compound Domain Adaptationcited by 76
  23. 2020Learning Invariant Representations and Risks for Semi-supervised Domain Adaptationcited by 69
  24. 2023Instance-aware Dynamic Prompt Tuning for Pre-trained Point Cloud Modelscited by 67
  25. 2016FPNN: Field Probing Neural Networks for 3D Datacited by 25
  26. 2019Dominant Set Clustering and Pooling for Multi-View 3D Object Recognitioncited by 25
  27. 2024GPSFormer: A Global Perception and Local Structure Fitting-based Transformer for Point Cloud Understandingcited by 12
  28. 2021Continuous Conditional Random Field Convolution for Point Cloud Segmentationcited by 7

Built on by

Not cited yet.