mlsanityData to 7 Oct 2026

Window Normalization: Enhancing Point Cloud Understanding by Unifying Inconsistent Point Densities

arXiv 2212.02287 ↗First posted 5 Dec 2022cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

Downsampling and feature extraction are essential procedures for 3D point cloud understanding. Existing methods are limited by the inconsistent point densities of different parts in the point cloud. In this work, we analyze the limitation of the downsampling stage and propose the pre-abstraction group-wise window-normalization module. In particular, the window-normalization method is leveraged to unify the point densities in different parts. Furthermore, the group-wise strategy is proposed to obtain multi-type features, including texture and spatial information. We also propose the pre-abstraction module to balance local and global features. Extensive experiments show that our module performs better on several tasks. In segmentation tasks on S3DIS (Area 5), the proposed module performs better on small object recognition, and the results have more precise boundaries than others. The recognition of the sofa and the column is improved from 69.2% to 84.4% and from 42.7% to 48.7%, respectively. The benchmarks are improved from 71.7%/77.6%/91.9% (mIoU/mAcc/OA) to 72.2%/78.2%/91.4%. The accuracies of 6-fold cross-validation on S3DIS are 77.6%/85.8%/91.7%. It outperforms the best model PointNeXt-XL (74.9%/83.0%/90.3%) by 2.7% on mIoU and achieves state-of-the-art performance. The code and models are available at https://github.com/DBDXSS/Window-Normalization.git.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 37 of its 47 references that are in the map. First posted on arXiv 5 Dec 2022.

Builds on

37 of 47 references.

References · 37

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  4. 2020End-to-End Object Detection with Transformerscited by 7,384
  5. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  6. 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
  7. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  8. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,707
  9. 2020Point Transformercited by 1,462
  10. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  11. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,201
  12. 2021Going deeper with Image Transformerscited by 759
25 more
  1. 2021PVT v2: Improved Baselines with Pyramid Vision Transformercited by 749
  2. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 746
  3. 2020PCT: Point cloud transformercited by 730
  4. 2016Multi-View 3D Object Detection Network for Autonomous Drivingcited by 721
  5. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 584
  6. 2021Twins: Revisiting the Design of Spatial Attention in Vision Transformerscited by 565
  7. 2015Multi-view Convolutional Neural Networks for 3D Shape Recognitioncited by 564
  8. 2021CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windowscited by 526
  9. 2016Semantic Scene Completion from a Single Depth Imagecited by 468
  10. 2022PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategiescited by 432
  11. 2022Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Frameworkcited by 376
  12. 2016OctNet: Learning Deep 3D Representations at High Resolutionscited by 340
  13. 2021Voxel Transformer for 3D Object Detectioncited by 247
  14. 2020PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Samplingcited by 238
  15. 2021Group-Free 3D Object Detection via Transformerscited by 215
  16. 2021PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Cloudscited by 211
  17. 2018Tangent Convolutions for Dense Prediction in 3Dcited by 173
  18. 2022Stratified Transformer for 3D Point Cloud Segmentationcited by 166
  19. 2019Modeling Point Clouds with Self-Attention and Gumbel Subset Samplingcited by 151
  20. 2016Vehicle Detection from 3D Lidar Using Fully Convolutional Networkcited by 105
  21. 2020JSENet: Joint Semantic Segmentation and Edge Detection Network for 3D Point Cloudscited by 62
  22. 2018PointSIFT: A SIFT-like Network Module for 3D Point Cloud Semantic Segmentationcited by 58
  23. 2021Visual Parser: Representing Part-whole Hierarchies with Transformerscited by 21
  24. 2021ICM-3D: Instantiated Category Modeling for 3D Instance Segmentationcited by 18
  25. 2019LSANet: Feature Learning on Point Sets by Local Spatial Aware Layercited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 2; 2025: 0; 2026: 1.

5 papers.

  1. 2023Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understandingcited by 111
  2. 2023Efficient 3D Semantic Segmentation with Superpoint Transformercited by 56
  3. 2024Scalable 3D Panoptic Segmentation As Superpoint Graph Clusteringcited by 14
  4. 2024Swin3D++: Effective Multi-Source Pretraining for 3D Indoor Scene Understandingcited by 6
  5. 2026Channel-Level Relation to Attentive Aggregation with Neighborhood-Homogeneity Constraint for Point Cloud Analysiscited by 0