mlsanityData to 14 Oct 2026

PIDS: Joint Point Interaction-Dimension Search for 3D Point Cloud

arXiv 2211.15759 ↗First posted 28 Nov 2022cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

The interaction and dimension of points are two important axes in designing point operators to serve hierarchical 3D models. Yet, these two axes are heterogeneous and challenging to fully explore. Existing works craft point operator under a single axis and reuse the crafted operator in all parts of 3D models. This overlooks the opportunity to better combine point interactions and dimensions by exploiting varying geometry/density of 3D point clouds. In this work, we establish PIDS, a novel paradigm to jointly explore point interactions and point dimensions to serve semantic segmentation on point cloud data. We establish a large search space to jointly consider versatile point interactions and point dimensions. This supports point operators with various geometry/density considerations. The enlarged search space with heterogeneous search components calls for a better ranking of candidate models. To achieve this, we improve the search space exploration by leveraging predictor-based Neural Architecture Search (NAS), and enhance the quality of prediction by assigning unique encoding to heterogeneous search components based on their priors. We thoroughly evaluate the networks crafted by PIDS on two semantic segmentation benchmarks, showing ~1% mIOU improvement on SemanticKITTI and S3DIS over state-of-the-art 3D models.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 39 of its 49 references that are in the map. First posted on arXiv 28 Nov 2022.

Builds on

39 of 49 references.

References · 39

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  3. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  4. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  5. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  6. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  7. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  8. 2018DARTS: Differentiable Architecture Searchcited by 1,798
  9. 2020Point Transformercited by 1,470
  10. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,208
  11. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,205
  12. 2017Learning Transferable Architectures for Scalable Image Recognitioncited by 1,101
27 more
  1. 2018Regularized Evolution for Image Classifier Architecture Searchcited by 909
  2. 2019Once-for-All: Train One Network and Specialize it for Efficient Deploymentcited by 787
  3. 2016Wide & Deep Learning for Recommender Systemscited by 747
  4. 2020PCT: Point cloud transformercited by 732
  5. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 585
  6. 2020Searching Efficient 3D Architectures with Sparse Point-Voxel Convolutioncited by 423
  7. 2020PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentationcited by 275
  8. 2018SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filterscited by 261
  9. 2020SalsaNext: Fast, Uncertainty-aware Semantic Segmentation of LiDAR Point Clouds for Autonomous Drivingcited by 226
  10. 2020BigNAS: Scaling Up Neural Architecture Search with Big Single-Stage Modelscited by 188
  11. 2021(AF)2-S3Net: Attentive Feature Fusion with Adaptive Feature Selection for Sparse Semantic Segmentation Networkcited by 164
  12. 20222DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Cloudscited by 158
  13. 2018Point Convolutional Neural Networks by Extension Operatorscited by 154
  14. 2021Revisiting Point Cloud Shape Classification with a Simple and Effective Baselinecited by 145
  15. 2019Neural Predictor for Neural Architecture Searchcited by 118
  16. 2020Cylinder3D: An Effective 3D Framework for Driving-scene LiDAR Semantic Segmentationcited by 112
  17. 2020BRP-NAS: Prediction-based NAS using GCNscited by 111
  18. 2021Panoptic-PolarNet: Proposal-free LiDAR Point Cloud Panoptic Segmentationcited by 107
  19. 2019Interpolated Convolutional Networks for 3D Point Cloud Understandingcited by 86
  20. 2019SampleNet: Differentiable Point Cloud Samplingcited by 74
  21. 2021Semantic Segmentation for Real Point Cloud Scenes via Bilateral Augmentation and Adaptive Fusioncited by 72
  22. 2020JSENet: Joint Semantic Segmentation and Edge Detection Network for 3D Point Cloudscited by 62
  23. 2020FPConv: Learning Local Flattening for Point Convolutioncited by 55
  24. 2021PatchFormer: An Efficient Point Transformer with Patch Attentioncited by 43
  25. 2021Learning Inner-Group Relations on Point Cloudscited by 29
  26. 2021Homogeneous Architecture Augmentation for Neural Predictorcited by 14
  27. 2021Differentiable Convolution Search for Point Cloud Processingcited by 3

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 1; 2025: 1.

3 papers.

  1. 2023Segment Any Point Cloud Sequences by Distilling Vision Foundation Modelscited by 125
  2. 2024Evolutionary Neural Architecture Search for 3D Point Cloud Analysiscited by 1
  3. 2025FractalCloud: A Fractal-Inspired Architecture for Efficient Large-Scale Point Cloud Processingcited by 0