mlsanityData to 7 Oct 2026

Escape from Cells: Deep Kd-Networks for the Recognition of 3D Point Cloud Models

arXiv 1704.01222 ↗First posted 4 Apr 2017cs.CVcited by 142

Not on the map. Why?

Abstract (arXiv)

We present a new deep learning architecture (called Kd-network) that is designed for 3D model recognition tasks and works with unstructured point clouds. The new architecture performs multiplicative transformations and share parameters of these transformations according to the subdivisions of the point clouds imposed onto them by Kd-trees. Unlike the currently dominant convolutional architectures that usually require rasterization on uniform two-dimensional or three-dimensional grids, Kd-networks do not rely on such grids in any way and therefore avoid poor scaling behaviour. In a series of experiments with popular shape recognition benchmarks, Kd-networks demonstrate competitive performance in a number of shape recognition tasks such as shape classification, shape retrieval and shape part segmentation.

Key facts. Cited by 142 papers in the map (data through 7 Oct 2026). First posted on arXiv 4 Apr 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 66; 2022: 31; 2023: 20; 2024: 17; 2025: 4; 2026: 4.

142 papers.

Sort:

By area:

  1. 2021Self-Supervised Pretraining of 3D Features on any Point-Cloudcited by 217
  2. 2021PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Cloudscited by 211
  3. 2021Spatio-temporal Self-Supervised Representation Learning for 3D Point Cloudscited by 180
  4. 2021Walk in the Cloud: Learning Curves for Point Clouds Shape Analysiscited by 172
  5. 2021Revisiting Point Cloud Shape Classification with a Simple and Effective Baselinecited by 145
  6. 2021Beyond Self-attention: External Attention using Two Linear Layers for Visual Taskscited by 109
  7. 2022Surface Representation for Point Cloudscited by 84
  8. 2021Learning to Stylize Novel Viewscited by 76
  9. 20213D Semantic Scene Completion: a Surveycited by 74
  10. 2022P2P: Tuning Pre-trained Image Models for Point Cloud Analysis with Point-to-Pixel Promptingcited by 74
  11. 2021PointMixer: MLP-Mixer for Point Cloud Understandingcited by 71
  12. 2021Subdivision-Based Mesh Convolution Networkscited by 60
38 more
  1. 2021Adaptive Graph Convolution for Point Cloud Analysiscited by 60
  2. 2021Regularization Strategy for Point Cloud via Rigidly Mixed Samplecited by 59
  3. 2021Semantics for Robotic Mapping, Perception and Interaction: A Surveycited by 56
  4. 2021SSPC-Net: Semi-supervised Semantic 3D Point Cloud Segmentation Networkcited by 54
  5. 2021Self-Contrastive Learning with Hard Negative Sampling for Self-supervised Point Cloud Learningcited by 52
  6. 2021A Survey on Deep Domain Adaptation for LiDAR Perceptioncited by 46
  7. 2021PVT: Point-Voxel Transformer for Point Cloud Learningcited by 42
  8. 2021Image2Point: 3D Point-Cloud Understanding with 2D Image Pretrained Modelscited by 41
  9. 2023Smooth, exact rotational symmetrization for deep learning on point cloudscited by 39
  10. 2021RandomRooms: Unsupervised Pre-training from Synthetic Shapes and Randomized Layouts for 3D Object Detectioncited by 37
  11. 2021Learning from 2D: Contrastive Pixel-to-Point Knowledge Transfer for 3D Pretrainingcited by 32
  12. 2021Deep Learning Based 3D Segmentation: A Surveycited by 30
  13. 2022Masked Autoencoders in 3D Point Cloud Representation Learningcited by 30
  14. 2021Learning Inner-Group Relations on Point Cloudscited by 29
  15. 2022RIConv++: Effective Rotation Invariant Convolutions for 3D Point Clouds Deep Learningcited by 29
  16. 2021Dual Transformer for Point Cloud Analysiscited by 26
  17. 2023Take-A-Photo: 3D-to-2D Generative Pre-training of Point Cloud Modelscited by 25
  18. 2023Deep Learning-based 3D Point Cloud Classification: A Systematic Survey and Outlookcited by 24
  19. 2021Learning with Noisy Labels for Robust Point Cloud Segmentationcited by 22
  20. 2022LCPFormer: Towards Effective 3D Point Cloud Analysis via Local Context Propagation in Transformerscited by 21
  21. 2022Flattening-Net: Deep Regular 2D Representation for 3D Point Cloud Analysiscited by 19
  22. 2022PVNAS: 3D Neural Architecture Search with Point-Voxel Convolutioncited by 16
  23. 2021PRIN/SPRIN: On Extracting Point-wise Rotation Invariant Featurescited by 15
  24. 2021Point Cloud Learning with Transformercited by 15
  25. 2022AGConv: Adaptive Graph Convolution on 3D Point Cloudscited by 13
  26. 2021Learning Rotation-Invariant Representations of Point Clouds Using Aligned Edge Convolutional Neural Networkscited by 12
  27. 2021Improvement of Normal Estimation for PointClouds via Simplifying Surface Fittingcited by 12
  28. 2021A new weakly supervised approach for ALS point cloud semantic segmentationcited by 12
  29. 2022Depth Completion using Geometry-Aware Embeddingcited by 12
  30. 2022Teacher-Student Network for 3D Point Cloud Anomaly Detection with Few Normal Samplescited by 12
  31. 2022Laplacian2Mesh: Laplacian-Based Mesh Understandingcited by 11
  32. 2022SemAffiNet: Semantic-Affine Transformation for Point Cloud Segmentationcited by 11
  33. 2021FatNet: A Feature-attentive Network for 3D Point Cloud Processingcited by 10
  34. 2021Simultaneous Multi-View Object Recognition and Grasping in Open-Ended Domainscited by 10
  35. 2022PointMCD: Boosting Deep Point Cloud Encoders via Multi-view Cross-modal Distillation for 3D Shape Recognitioncited by 10
  36. 20233DInAction: Understanding Human Actions in 3D Point Cloudscited by 10
  37. 2021Exploiting Local Geometry for Feature and Graph Construction for Better 3D Point Cloud Processing with Graph Neural Networkscited by 9
  38. 2021Learning Scene Dynamics from Point Cloud Sequencescited by 9

50 most cited of 142 All 142 (JSON)