mlsanityData to 7 Oct 2026

Robust Point Cloud Processing through Positional Embedding

arXiv 2309.00339 ↗First posted 1 Sep 2023cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

End-to-end trained per-point embeddings are an essential ingredient of any state-of-the-art 3D point cloud processing such as detection or alignment. Methods like PointNet, or the more recent point cloud transformer -- and its variants -- all employ learned per-point embeddings. Despite impressive performance, such approaches are sensitive to out-of-distribution (OOD) noise and outliers. In this paper, we explore the role of an analytical per-point embedding based on the criterion of bandwidth. The concept of bandwidth enables us to draw connections with an alternate per-point embedding -- positional embedding, particularly random Fourier features. We present compelling robust results across downstream tasks such as point cloud classification and registration with several categories of OOD noise.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 26 of its 37 references that are in the map. First posted on arXiv 1 Sep 2023.

Builds on

26 of 37 references.

References · 26

  1. 2017Attention Is All You Needcited by 59,932
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  4. 2018Neural Tangent Kernel: Convergence and Generalization in Neural Networkscited by 2,597
  5. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  6. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,170
  7. 2020Point Transformercited by 1,462
  8. 2017Deep Setscited by 1,394
  9. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  10. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 774
  11. 2019Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descentcited by 732
  12. 2020PCT: Point cloud transformercited by 730
14 more
  1. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 656
  2. 2018Gradient Descent Provably Optimizes Over-parameterized Neural Networkscited by 655
  3. 2017Frustum PointNets for 3D Object Detection from RGB-D Datacited by 640
  4. 2019Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networkscited by 562
  5. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
  6. 2019PointNetLK: Robust & Efficient Point Cloud Registration using PointNetcited by 231
  7. 2019On the Inductive Bias of Neural Tangent Kernelscited by 177
  8. 2022Benchmarking Robustness of 3D Point Cloud Recognition Against Common Corruptionscited by 78
  9. 2019Reconstructing continuous distributions of 3D protein structure from cryo-EM imagescited by 56
  10. 2021Rethinking Positional Encodingcited by 36
  11. 2022Trading Positional Complexity vs. Deepness in Coordinate Networkscited by 16
  12. 2019On Deep Set Learning and the Choice of Aggregationscited by 13
  13. 2020How Powerful Are Randomly Initialized Pointcloud Set Functions?cited by 3
  14. 2021Robust Pooling through the Data Modecited by 1

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 3; 2025: 1.

5 papers.

  1. 2024No Time to Train: Empowering Non-Parametric Networks for Few-shot 3D Scene Segmentationcited by 18
  2. 20233D-LFM: Lifting Foundation Modelcited by 8
  3. 2024Fast Kernel Scene Flowcited by 1
  4. 2024Object Agnostic 3D Lifting in Space and Timecited by 0
  5. 20253D Gaussian Point Encoderscited by 0