mlsanityData to 7 Oct 2026

Complete-to-Partial 4D Distillation for Self-Supervised Point Cloud Sequence Representation Learning

arXiv 2212.05330 ↗First posted 10 Dec 2022cs.CVcited by 30

Not on the map. Why?

Abstract (arXiv)

Recent work on 4D point cloud sequences has attracted a lot of attention. However, obtaining exhaustively labeled 4D datasets is often very expensive and laborious, so it is especially important to investigate how to utilize raw unlabeled data. However, most existing self-supervised point cloud representation learning methods only consider geometry from a static snapshot omitting the fact that sequential observations of dynamic scenes could reveal more comprehensive geometric details. And the video representation learning frameworks mostly model motion as image space flows, let alone being 3D-geometric-aware. To overcome such issues, this paper proposes a new 4D self-supervised pre-training method called Complete-to-Partial 4D Distillation. Our key idea is to formulate 4D self-supervised representation learning as a teacher-student knowledge distillation framework and let the student learn useful 4D representations with the guidance of the teacher. Experiments show that this approach significantly outperforms previous pre-training approaches on a wide range of 4D point cloud sequence understanding tasks including indoor and outdoor scenarios.

Key facts. Cited by 30 papers in the map (data through 7 Oct 2026). Builds on 30 of its 36 references that are in the map. First posted on arXiv 10 Dec 2022.

Builds on

30 of 36 references.

References · 30

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  2. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  3. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  4. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  5. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,201
  6. 2021Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modelingcited by 647
  7. 2020PointContrast: Unsupervised Pre-training for 3D Point Cloud Understandingcited by 502
  8. 2021PointCLIP: Point Cloud Understanding by CLIPcited by 461
  9. 2022Masked Autoencoders for Point Cloud Self-supervised Learningcited by 456
  10. 2017Time-Contrastive Networks: Self-Supervised Learning from Videocited by 453
  11. 2022Masked Autoencoders As Spatiotemporal Learnerscited by 428
  12. 2022HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interactioncited by 321
18 more
  1. 2022Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-trainingcited by 263
  2. 2021Self-Supervised Pretraining of 3D Features on any Point-Cloudcited by 217
  3. 2020Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contextscited by 210
  4. 2020Unsupervised Point Cloud Pre-Training via Occlusion Completioncited by 186
  5. 2021Spatio-temporal Self-Supervised Representation Learning for 3D Point Cloudscited by 180
  6. 2021TCLR: Temporal Contrastive Learning for Video Representationcited by 136
  7. 2019MeteorNet: Deep Learning on Dynamic 3D Point Cloud Sequencescited by 117
  8. 2022PSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequencescited by 68
  9. 20214DContrast: Contrastive Learning with Dynamic Correspondences for 3D Scene Understandingcited by 54
  10. 2020Learning Physical Graph Representations from Visual Scenescited by 50
  11. 2021Contrastive Multimodal Fusion with TupleInfoNCEcited by 43
  12. 2020P4Contrast: Contrastive Learning with Pairs of Point-Pixel Pairs for RGB-D Scene Understandingcited by 41
  13. 2021RandomRooms: Unsupervised Pre-training from Synthetic Shapes and Randomized Layouts for 3D Object Detectioncited by 37
  14. 2021ASCNet: Self-supervised Video Representation Learning with Appearance-Speed Consistencycited by 35
  15. 2022Point Primitive Transformer for Long-Term 4D Point Cloud Video Understandingcited by 35
  16. 2021TCGL: Temporal Contrastive Graph for Self-supervised Video Representation Learningcited by 31
  17. 2022Distillation with Contrast is All You Need for Self-Supervised Point Cloud Representation Learningcited by 19
  18. 2022Learning Spatial and Temporal Variations for 4D Point Cloud Segmentationcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 6; 2024: 9; 2025: 6; 2026: 9.

30 papers.

Sort:

By area:

  1. 2023Segment Any Point Cloud Sequences by Distilling Vision Foundation Modelscited by 123
  2. 2023An Outlook into the Future of Egocentric Visioncited by 84
  3. 20244D Contrastive Superflows are Dense 3D Representation Learnerscited by 32
  4. 2023Masked Spatio-Temporal Structure Prediction for Self-supervised Learning on Point Cloud Videoscited by 19
  5. 2024ImOV3D: Learning Open-Vocabulary Point Clouds 3D Object Detection from Only 2D Imagescited by 17
  6. 2026Align then Adapt: Rethinking Parameter-Efficient Transfer Learning in 4D Perceptioncited by 17
  7. 2023Point Contrastive Prediction with Semantic Clustering for Self-Supervised Learning on Point Cloud Videoscited by 16
  8. 2023X4D-SceneFormer: Enhanced Scene Understanding on 4D Point Cloud Videos through Cross-modal Knowledge Transfercited by 12
  9. 2024MAMBA4D: Efficient Long-Sequence Point Cloud Video Understanding with Disentangled Spatial-Temporal State Space Modelscited by 11
  10. 2024Shelf-Supervised Cross-Modal Pre-Training for 3D Object Detectioncited by 9
  11. 20254D Visual Pre-training for Robot Learningcited by 8
  12. 2024CrossVideo: Self-supervised Cross-modal Contrastive Learning for Point Cloud Video Understandingcited by 6
18 more
  1. 2026Diffusion Masked Pretraining for Dynamic Point Cloudcited by 6
  2. 2024Fine-grained Image-to-LiDAR Contrastive Distillation with Visual Foundation Modelscited by 5
  3. 2026Tri-Efficient Transfer Learning for Point Cloud Videoscited by 5
  4. 2025Enhanced Spatiotemporal Consistency for Image-to-LiDAR Data Pretrainingcited by 4
  5. 2024A Unified Framework for Human-centric Point Cloud Video Understandingcited by 3
  6. 2024KAN-HyperpointNet for Point Cloud Sequence-Based 3D Human Action Recognitioncited by 3
  7. 2025Uni4D: A Unified Self-Supervised Learning Framework for Point Cloud Videoscited by 3
  8. 2024ESP-PCT: Enhanced VR Semantic Performance through Efficient Compression of Temporal and Spatial Redundancies in Point Cloud Transformerscited by 2
  9. 2025Content-Distortion High-Order Interaction for Blind Image Quality Assessmentcited by 2
  10. 2023Point Cloud Video Anomaly Detection Based on Point Spatio-Temporal Auto-Encodercited by 1
  11. 2025DeSPITE: Exploring Contrastive Deep Skeleton-Pointcloud-IMU-Text Embeddings for Advanced Point Cloud Human Activity Understandingcited by 1
  12. 2025PointNet4D: A Lightweight 4D Point Cloud Video Backbone for Online and Offline Perception in Robotic Applicationscited by 1
  13. 2026STS-Mixer: Spatio-Temporal-Spectral Mixer for 4D Point Cloud Video Understandingcited by 1
  14. 2026Cross4D-JEPA: Dense Cross-modal Correspondence Distillation for 4D Point Cloud Representation Learningcited by 1
  15. 2026GATS: Gaussian Aware Temporal Scaling Transformer for Invariant 4D Spatio-Temporal Point Cloud Representationcited by 0
  16. 2026Paving the Way for Point Cloud Video Representation Learning Using A PDE Modelcited by 0
  17. 2026Joint-Embedding Prediction of Masked Point Tubes for Self-Supervised Learning on 4D Point Cloud Videoscited by 0
  18. 2026Motion-Saliency Complementary Masked Modeling for Point Cloud Video Understandingcited by 0