mlsanityData to 7 Oct 2026

Implicit Autoencoder for Point-Cloud Self-Supervised Representation Learning

arXiv 2201.00785 ↗First posted 3 Jan 2022cs.CVcited by 46

Not on the map. Why?

Abstract (arXiv)

This paper advocates the use of implicit surface representation in autoencoder-based self-supervised 3D representation learning. The most popular and accessible 3D representation, i.e., point clouds, involves discrete samples of the underlying continuous 3D surface. This discretization process introduces sampling variations on the 3D shape, making it challenging to develop transferable knowledge of the true 3D geometry. In the standard autoencoding paradigm, the encoder is compelled to encode not only the 3D geometry but also information on the specific discrete sampling of the 3D shape into the latent code. This is because the point cloud reconstructed by the decoder is considered unacceptable unless there is a perfect mapping between the original and the reconstructed point clouds. This paper introduces the Implicit AutoEncoder (IAE), a simple yet effective method that addresses the sampling variation issue by replacing the commonly-used point-cloud decoder with an implicit decoder. The implicit decoder reconstructs a continuous representation of the 3D shape, independent of the imperfections in the discrete samples. Extensive experiments demonstrate that the proposed IAE achieves state-of-the-art performance across various self-supervised learning benchmarks.

Key facts. Cited by 46 papers in the map (data through 7 Oct 2026). Builds on 60 of its 96 references that are in the map. First posted on arXiv 3 Jan 2022.

Builds on

60 of 96 references.

References · 60

  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. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  5. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  6. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  7. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  8. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  9. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  10. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  11. 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,838
  12. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,586
38 more
  1. 2020Point Transformercited by 1,462
  2. 2016Context Encoders: Feature Learning by Inpaintingcited by 1,424
  3. 2016Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzlescited by 1,379
  4. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  5. 2016Colorful Image Colorizationcited by 1,113
  6. 2015Unsupervised Visual Representation Learning by Context Predictioncited by 1,062
  7. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  8. 2018Deep Clustering for Unsupervised Learning of Visual Featurescited by 1,020
  9. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 972
  10. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  11. 2020Convolutional Occupancy Networkscited by 760
  12. 2019Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervisioncited by 699
  13. 2019Deep Hough Voting for 3D Object Detection in Point Cloudscited by 648
  14. 2021Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modelingcited by 647
  15. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 584
  16. 2016Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modelingcited by 558
  17. 2019Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Datacited by 532
  18. 2020PointContrast: Unsupervised Pre-training for 3D Point Cloud Understandingcited by 502
  19. 2018PCN: Point Completion Networkcited by 382
  20. 2021An End-to-End Transformer Model for 3D Object Detectioncited by 329
  21. 2020Neural Unsigned Distance Fields for Implicit Function Learningcited by 265
  22. 2019Learning Shape Templates with Structured Implicit Functionscited by 242
  23. 2021Self-Supervised Pretraining of 3D Features on any Point-Cloudcited by 217
  24. 2021Group-Free 3D Object Detection via Transformerscited by 215
  25. 2018SO-Net: Self-Organizing Network for Point Cloud Analysiscited by 210
  26. 2019Texture Fields: Learning Texture Representations in Function Spacecited by 210
  27. 2019Local Aggregation for Unsupervised Learning of Visual Embeddingscited by 204
  28. 2020Unsupervised Point Cloud Pre-Training via Occlusion Completioncited by 186
  29. 2021Spatio-temporal Self-Supervised Representation Learning for 3D Point Cloudscited by 180
  30. 2019DIST: Rendering Deep Implicit Signed Distance Function with Differentiable Sphere Tracingcited by 179
  31. 2021SnowflakeNet: Point Cloud Completion by Snowflake Point Deconvolution with Skip-Transformercited by 162
  32. 20203D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentationcited by 140
  33. 2018Recent Advances in Autoencoder-Based Representation Learningcited by 130
  34. 2019Learning to Infer Implicit Surfaces without 3D Supervisioncited by 103
  35. 2021FCAF3D: Fully Convolutional Anchor-Free 3D Object Detectioncited by 97
  36. 2020ParSeNet: A Parametric Surface Fitting Network for 3D Point Cloudscited by 96
  37. 2019Unsupervised Multi-Task Feature Learning on Point Cloudscited by 89
  38. 2020MLCVNet: Multi-Level Context VoteNet for 3D Object Detectioncited by 80

50 most cited of 60 All 60 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 13; 2023: 17; 2024: 10; 2025: 5; 2026: 1.

46 papers.

Sort:

By area:

  1. 2022Masked Autoencoders for Point Cloud Self-supervised Learningcited by 456
  2. 2022Masked Discrimination for Self-Supervised Learning on Point Cloudscited by 155
  3. 2023Segment Any Point Cloud Sequences by Distilling Vision Foundation Modelscited by 123
  4. 2023PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigmcited by 56
  5. 2022Ponder: Point Cloud Pre-training via Neural Renderingcited by 50
  6. 2024Binocular-Guided 3D Gaussian Splatting with View Consistency for Sparse View Synthesiscited by 41
  7. 2024ViGoR: Improving Visual Grounding of Large Vision Language Models with Fine-Grained Reward Modelingcited by 34
  8. 2023Self-supervised Learning for Pre-Training 3D Point Clouds: A Surveycited by 21
  9. 2022MAELi: Masked Autoencoder for Large-Scale LiDAR Point Cloudscited by 20
  10. 2023SGRec3D: Self-Supervised 3D Scene Graph Learning via Object-Level Scene Reconstructioncited by 20
  11. 2024NeRF-MAE: Masked AutoEncoders for Self-Supervised 3D Representation Learning for Neural Radiance Fieldscited by 20
  12. 20223D-OAE: Occlusion Auto-Encoders for Self-Supervised Learning on Point Cloudscited by 18
34 more
  1. 2022HiP: Hierarchical Perceivercited by 15
  2. 2022Masked Surfel Prediction for Self-Supervised Point Cloud Learningcited by 15
  3. 20233D Feature Prediction for Masked-AutoEncoder-Based Point Cloud Pretrainingcited by 13
  4. 2023Self-supervised Pre-training with Masked Shape Prediction for 3D Scene Understandingcited by 13
  5. 2022Point-DAE: Denoising Autoencoders for Self-supervised Point Cloud Learningcited by 9
  6. 2023ACL-SPC: Adaptive Closed-Loop system for Self-Supervised Point Cloud Completioncited by 9
  7. 2023NaviNeRF: NeRF-based 3D Representation Disentanglement by Latent Semantic Navigationcited by 8
  8. 2024Shape2Scene: 3D Scene Representation Learning Through Pre-training on Shape Datacited by 8
  9. 2025The quest for the GRAph Level autoEncoder (GRALE)cited by 8
  10. 20223D Point Cloud Pre-training with Knowledge Distillation from 2D Imagescited by 7
  11. 2022Pix4Point: Image Pretrained Standard Transformers for 3D Point Cloud Understandingcited by 6
  12. 2022DeepMend: Learning Occupancy Functions to Represent Shape for Repaircited by 6
  13. 2025UniPre3D: Unified Pre-training of 3D Point Cloud Models with Cross-Modal Gaussian Splattingcited by 6
  14. 2022DeepJoin: Learning a Joint Occupancy, Signed Distance, and Normal Field Function for Shape Repaircited by 5
  15. 20233D-QAE: Fully Quantum Auto-Encoding of 3D Point Cloudscited by 5
  16. 2024Multi-modal Relation Distillation for Unified 3D Representation Learningcited by 5
  17. 2025Conditional Representation Learning for Customized Taskscited by 5
  18. 2023PointPatchMix: Point Cloud Mixing with Patch Scoringcited by 4
  19. 2023PRISE: Demystifying Deep Lucas-Kanade with Strongly Star-Convex Constraints for Multimodel Image Alignmentcited by 4
  20. 2023PointGame: Geometrically and Adaptively Masked Auto-Encoder on Point Cloudscited by 4
  21. 2022SeRP: Self-Supervised Representation Learning Using Perturbed Point Cloudscited by 3
  22. 2023GTNet: Graph Transformer Network for 3D Point Cloud Classification and Semantic Segmentationcited by 3
  23. 2023Multi-View Representation is What You Need for Point-Cloud Pre-Trainingcited by 3
  24. 2023PatchContrast: Self-Supervised Pre-training for 3D Object Detectioncited by 3
  25. 2024TREND: Unsupervised 3D Representation Learning via Temporal Forecasting for LiDAR Perceptioncited by 2
  26. 2023Sampled Transformer for Point Setscited by 1
  27. 2024Triple Point Maskingcited by 1
  28. 2024Point Cloud Unsupervised Pre-training via 3D Gaussian Splattingcited by 1
  29. 2024CLAP: Unsupervised 3D Representation Learning for Fusion 3D Perception via Curvature Sampling and Prototype Learningcited by 1
  30. 2025Physics-Driven Local-Whole Elastic Deformation Modeling for Point Cloud Representation Learningcited by 1
  31. 2023Self-supervised adversarial masking for 3D point cloud representation learningcited by 0
  32. 2024PointCG: Self-supervised Point Cloud Learning via Joint Completion and Generationcited by 0
  33. 2025Multi-modal Multi-task Pre-training for Improved Point Cloud Understandingcited by 0
  34. 2026Semantic Purification for Conditional Representation Learningcited by 0