mlsanityData to 7 Oct 2026

ACL-SPC: Adaptive Closed-Loop system for Self-Supervised Point Cloud Completion

arXiv 2303.01979 ↗First posted 2 Mar 2023cs.CVcited by 9

Not on the map. Why?

Abstract (arXiv)

Point cloud completion addresses filling in the missing parts of a partial point cloud obtained from depth sensors and generating a complete point cloud. Although there has been steep progress in the supervised methods on the synthetic point cloud completion task, it is hardly applicable in real-world scenarios due to the domain gap between the synthetic and real-world datasets or the requirement of prior information. To overcome these limitations, we propose a novel self-supervised framework ACL-SPC for point cloud completion to train and test on the same data. ACL-SPC takes a single partial input and attempts to output the complete point cloud using an adaptive closed-loop (ACL) system that enforces the output same for the variation of an input. We evaluate our proposed ACL-SPC on various datasets to prove that it can successfully learn to complete a partial point cloud as the first self-supervised scheme. Results show that our method is comparable with unsupervised methods and achieves superior performance on the real-world dataset compared to the supervised methods trained on the synthetic dataset. Extensive experiments justify the necessity of self-supervised learning and the effectiveness of our proposed method for the real-world point cloud completion task. The code is publicly available from https://github.com/Sangminhong/ACL-SPC_PyTorch

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 35 of its 56 references that are in the map. First posted on arXiv 2 Mar 2023.

Builds on

35 of 56 references.

References · 35

  1. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  2. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  3. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  4. 2017Matterport3D: Learning from RGB-D Data in Indoor Environmentscited by 1,354
  5. 2016Pixel Recurrent Neural Networkscited by 814
  6. 2016Generative Adversarial Text to Image Synthesiscited by 735
  7. 2017Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networkscited by 707
  8. 2020PointContrast: Unsupervised Pre-training for 3D Point Cloud Understandingcited by 502
  9. 2022Masked Autoencoders for Point Cloud Self-supervised Learningcited by 456
  10. 2018PCN: Point Completion Networkcited by 382
  11. 2021PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformerscited by 284
  12. 2017Learning to Discover Cross-Domain Relations with Generative Adversarial Networkscited by 278
23 more
  1. 2019Libra R-CNN: Towards Balanced Learning for Object Detectioncited by 255
  2. 2016Shape Completion using 3D-Encoder-Predictor CNNs and Shape Synthesiscited by 219
  3. 2022CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understandingcited by 198
  4. 2020GRNet: Gridding Residual Network for Dense Point Cloud Completioncited by 174
  5. 2021SnowflakeNet: Point Cloud Completion by Snowflake Point Deconvolution with Skip-Transformercited by 162
  6. 2022Masked Discrimination for Self-Supervised Learning on Point Cloudscited by 155
  7. 2020Cascaded Refinement Network for Point Cloud Completioncited by 112
  8. 2018Unsupervised Learning of Shape and Pose with Differentiable Point Cloudscited by 89
  9. 2022SeedFormer: Patch Seeds based Point Cloud Completion with Upsample Transformercited by 83
  10. 2021Unsupervised 3D Shape Completion through GAN Inversioncited by 70
  11. 2019Unpaired Point Cloud Completion on Real Scans using Adversarial Trainingcited by 66
  12. 2020Self-Supervised Few-Shot Learning on Point Cloudscited by 66
  13. 2021Moving Object Segmentation in 3D LiDAR Data: A Learning-based Approach Exploiting Sequential Datacited by 64
  14. 2021Self-Contrastive Learning with Hard Negative Sampling for Self-supervised Point Cloud Learningcited by 52
  15. 2016VConv-DAE: Deep Volumetric Shape Learning Without Object Labelscited by 50
  16. 2021Cycle4Completion: Unpaired Point Cloud Completion using Cycle Transformation with Missing Region Codingcited by 50
  17. 2022Implicit Autoencoder for Point-Cloud Self-Supervised Representation Learningcited by 46
  18. 2020Weakly-supervised 3D Shape Completion in the Wildcited by 33
  19. 2022Self-Supervised Arbitrary-Scale Point Clouds Upsampling via Implicit Neural Representationcited by 24
  20. 2022FBNet: Feedback Network for Point Cloud Completioncited by 20
  21. 2021Self-Supervised Point Cloud Completion via Inpaintingcited by 16
  22. 2021PolyNet: Polynomial Neural Network for 3D Shape Recognition with PolyShape Representationcited by 9
  23. 2017Learning quadrangulated patches for 3D shape parameterization and completioncited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 4; 2025: 2; 2026: 2.

9 papers.

  1. 2023P2C: Self-Supervised Point Cloud Completion from Single Partial Cloudscited by 19
  2. 2024Explicitly Guided Information Interaction Network for Cross-modal Point Cloud Completioncited by 9
  3. 2025GenPC: Zero-shot Point Cloud Completion via 3D Generative Priorscited by 9
  4. 2026LaS-Comp: Zero-shot 3D Completion with Latent-Spatial Consistencycited by 9
  5. 20243D Shape Completion on Unseen Categories:A Weakly-supervised Approachcited by 6
  6. 2024Unsupervised 3D Point Cloud Completion via Multi-view Adversarial Learningcited by 6
  7. 2024Point-In-Context: Understanding Point Cloud via In-Context Learningcited by 4
  8. 2025Self-Supervised Large Scale Point Cloud Completion for Archaeological Site Restorationcited by 1
  9. 2026PrintAnything: Learning an Intermediate Representation for 3D printing G-code Generationcited by 0