mlsanityData to 7 Oct 2026

Point-Voxel CNN for Efficient 3D Deep Learning

arXiv 1907.03739 ↗First posted 8 Jul 2019cs.CVcited by 343

Not on the map. Why?

Cited by 46 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We present Point-Voxel CNN (PVCNN) for efficient, fast 3D deep learning. Previous work processes 3D data using either voxel-based or point-based NN models. However, both approaches are computationally inefficient. The computation cost and memory footprints of the voxel-based models grow cubically with the input resolution, making it memory-prohibitive to scale up the resolution. As for point-based networks, up to 80% of the time is wasted on structuring the sparse data which have rather poor memory locality, not on the actual feature extraction. In this paper, we propose PVCNN that represents the 3D input data in points to reduce the memory consumption, while performing the convolutions in voxels to reduce the irregular, sparse data access and improve the locality. Our PVCNN model is both memory and computation efficient. Evaluated on semantic and part segmentation datasets, it achieves much higher accuracy than the voxel-based baseline with 10x GPU memory reduction; it also outperforms the state-of-the-art point-based models with 7x measured speedup on average. Remarkably, the narrower version of PVCNN achieves 2x speedup over PointNet (an extremely efficient model) on part and scene segmentation benchmarks with much higher accuracy. We validate the general effectiveness of PVCNN on 3D object detection: by replacing the primitives in Frustrum PointNet with PVConv, it outperforms Frustrum PointNet++ by 2.4% mAP on average with 1.5x measured speedup and GPU memory reduction.

Key facts. Cited by 343 papers in the map (data through 7 Oct 2026). First posted on arXiv 8 Jul 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 63; 2022: 60; 2023: 86; 2024: 59; 2025: 54; 2026: 21.

343 papers.

Sort:

By area:

  1. 2022LION: Latent Point Diffusion Models for 3D Shape Generationcited by 552
  2. 20213D Shape Generation and Completion through Point-Voxel Diffusioncited by 516
  3. 2021PointCLIP: Point Cloud Understanding by CLIPcited by 461
  4. 2021Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesiscited by 459
  5. 2022PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategiescited by 432
  6. 2021PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformerscited by 284
  7. 2021PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detectioncited by 232
  8. 2021PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Cloudscited by 211
  9. 2021RPVNet: A Deep and Efficient Range-Point-Voxel Fusion Network for LiDAR Point Cloud Segmentationcited by 173
  10. 2024Scene-LLM: Extending Language Model for 3D Visual Understanding and Reasoningcited by 170
  11. 2022Stratified Transformer for 3D Point Cloud Segmentationcited by 166
  12. 2021FFB6D: A Full Flow Bidirectional Fusion Network for 6D Pose Estimationcited by 144
38 more
  1. 20223D Object Detection for Autonomous Driving: A Comprehensive Surveycited by 132
  2. 2022Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Cloudscited by 131
  3. 2022Solving 3D Inverse Problems using Pre-trained 2D Diffusion Modelscited by 130
  4. 2023Rethinking Range View Representation for LiDAR Segmentationcited by 126
  5. 2023State of the Art on Diffusion Models for Visual Computingcited by 126
  6. 2022Point-to-Voxel Knowledge Distillation for LiDAR Semantic Segmentationcited by 118
  7. 2023DiT-3D: Exploring Plain Diffusion Transformers for 3D Shape Generationcited by 110
  8. 20213D Object Detection for Autonomous Driving: A Surveycited by 106
  9. 2021Fast Point Transformercited by 103
  10. 2021A Conditional Point Diffusion-Refinement Paradigm for 3D Point Cloud Completioncited by 100
  11. 2022PillarNet: Real-Time and High-Performance Pillar-based 3D Object Detectioncited by 99
  12. 2021TPCN: Temporal Point Cloud Networks for Motion Forecastingcited by 94
  13. 2022Learning to Generate Realistic LiDAR Point Cloudscited by 91
  14. 2025PARTFIELD: Learning 3D Feature Fields for Part Segmentation and Beyondcited by 91
  15. 2023PC2: Projection-Conditioned Point Cloud Diffusion for Single-Image 3D Reconstructioncited by 84
  16. 2023OmniSeg3D: Omniversal 3D Segmentation via Hierarchical Contrastive Learningcited by 75
  17. 2021M3DeTR: Multi-representation, Multi-scale, Mutual-relation 3D Object Detection with Transformerscited by 74
  18. 2022TorchSparse: Efficient Point Cloud Inference Enginecited by 72
  19. 2023FlatFormer: Flattened Window Attention for Efficient Point Cloud Transformercited by 72
  20. 2021PointMixer: MLP-Mixer for Point Cloud Understandingcited by 71
  21. 2022ALSO: Automotive Lidar Self-supervision by Occupancy estimationcited by 68
  22. 2023AdaPoinTr: Diverse Point Cloud Completion with Adaptive Geometry-Aware Transformerscited by 65
  23. 2025CAD-Llama: Leveraging Large Language Models for Computer-Aided Design Parametric 3D Model Generationcited by 65
  24. 2021SQN: Weakly-Supervised Semantic Segmentation of Large-Scale 3D Point Cloudscited by 64
  25. 2023Texture Generation on 3D Meshes with Point-UV Diffusioncited by 63
  26. 2023Segment Anything in 3D with Radiance Fieldscited by 61
  27. 20213DStyleNet: Creating 3D Shapes with Geometric and Texture Style Variationscited by 58
  28. 2023UniSeg: A Unified Multi-Modal LiDAR Segmentation Network and the OpenPCSeg Codebasecited by 57
  29. 2022Fast Point Cloud Generation with Straight Flowscited by 56
  30. 2023Efficient 3D Semantic Segmentation with Superpoint Transformercited by 56
  31. 20213D Siamese Voxel-to-BEV Tracker for Sparse Point Cloudscited by 54
  32. 2021ReDAL: Region-based and Diversity-aware Active Learning for Point Cloud Semantic Segmentationcited by 52
  33. 2022STPLS3D: A Large-Scale Synthetic and Real Aerial Photogrammetry 3D Point Cloud Datasetcited by 52
  34. 2021Learning Semantic Segmentation of Large-Scale Point Clouds with Random Samplingcited by 51
  35. 2024AGG: Amortized Generative 3D Gaussians for Single Image to 3Dcited by 51
  36. 2022SensatUrban: Learning Semantics from Urban-Scale Photogrammetric Point Cloudscited by 49
  37. 2021VPFNet: Improving 3D Object Detection with Virtual Point based LiDAR and Stereo Data Fusioncited by 48
  38. 20233D Semantic Segmentation in the Wild: Learning Generalized Models for Adverse-Condition Point Cloudscited by 46

50 most cited of 343 All 343 (JSON)