mlsanityData to 7 Oct 2026

3D Adaptive Structural Convolution Network for Domain-Invariant Point Cloud Recognition

arXiv 2407.04833 ↗First posted 5 Jul 2024cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Adapting deep learning networks for point cloud data recognition in self-driving vehicles faces challenges due to the variability in datasets and sensor technologies, emphasizing the need for adaptive techniques to maintain accuracy across different conditions. In this paper, we introduce the 3D Adaptive Structural Convolution Network (3D-ASCN), a cutting-edge framework for 3D point cloud recognition. It combines 3D convolution kernels, a structural tree structure, and adaptive neighborhood sampling for effective geometric feature extraction. This method obtains domain-invariant features and demonstrates robust, adaptable performance on a variety of point cloud datasets, ensuring compatibility across diverse sensor configurations without the need for parameter adjustments. This highlights its potential to significantly enhance the reliability and efficiency of self-driving vehicle technology.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 16 of its 31 references that are in the map. First posted on arXiv 5 Jul 2024.

Builds on

16 of 31 references.

References · 16

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  2. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  4. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  5. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 890
  6. 2019Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Datacited by 532
  7. 2022PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategiescited by 432
  8. 2022Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Frameworkcited by 376
  9. 2020Train in Germany, Test in The USA: Making 3D Object Detectors Generalizecited by 150
  10. 2017Escape from Cells: Deep Kd-Networks for the Recognition of 3D Point Cloud Modelscited by 142
  11. 2020Deep Learning for LiDAR Point Clouds in Autonomous Driving: A Reviewcited by 114
  12. 2019A Survey of Deep Learning Applications to Autonomous Vehicle Controlcited by 101
4 more
  1. 2018Multiresolution Tree Networks for 3D Point Cloud Processingcited by 91
  2. 2018Recurrent Slice Networks for 3D Segmentation of Point Cloudscited by 82
  3. 2022TO-Scene: A Large-scale Dataset for Understanding 3D Tabletop Scenescited by 10
  4. 2023Sample-adaptive Augmentation for Point Cloud Recognition Against Real-world Corruptionscited by 6

Built on by

Not cited yet.