mlsanityData to 14 Oct 2026

Cascaded Refinement Network for Point Cloud Completion

arXiv 2004.03327 ↗First posted 7 Apr 2020cs.CVcited by 112

Not on the map. Why?

Abstract (arXiv)

Point clouds are often sparse and incomplete. Existing shape completion methods are incapable of generating details of objects or learning the complex point distributions. To this end, we propose a cascaded refinement network together with a coarse-to-fine strategy to synthesize the detailed object shapes. Considering the local details of partial input with the global shape information together, we can preserve the existing details in the incomplete point set and generate the missing parts with high fidelity. We also design a patch discriminator that guarantees every local area has the same pattern with the ground truth to learn the complicated point distribution. Quantitative and qualitative experiments on different datasets show that our method achieves superior results compared to existing state-of-the-art approaches on the 3D point cloud completion task. Our source code is available at https://github.com/xiaogangw/cascaded-point-completion.git.

Key facts. Cited by 112 papers in the map (data through 14 Oct 2026). First posted on arXiv 7 Apr 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 24; 2022: 35; 2023: 16; 2024: 18; 2025: 10; 2026: 9.

112 papers.

Sort:

By area:

  1. 2021PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformerscited by 286
  2. 2021SnowflakeNet: Point Cloud Completion by Snowflake Point Deconvolution with Skip-Transformercited by 164
  3. 2022Diffusion-SDF: Conditional Generative Modeling of Signed Distance Functionscited by 133
  4. 2021Density-aware Chamfer Distance as a Comprehensive Metric for Point Cloud Completioncited by 112
  5. 2021Variational Relational Point Completion Networkcited by 104
  6. 2021A Conditional Point Diffusion-Refinement Paradigm for 3D Point Cloud Completioncited by 100
  7. 2022SeedFormer: Patch Seeds based Point Cloud Completion with Upsample Transformercited by 83
  8. 20213D Semantic Scene Completion: a Surveycited by 74
  9. 2021Unsupervised 3D Shape Completion through GAN Inversioncited by 70
  10. 2023AdaPoinTr: Diverse Point Cloud Completion with Adaptive Geometry-Aware Transformerscited by 67
  11. 2022PMP-Net++: Point Cloud Completion by Transformer-Enhanced Multi-step Point Moving Pathscited by 57
  12. 2021Semantic Scene Completion via Integrating Instances and Scene in-the-Loopcited by 55
38 more
  1. 2021Cycle4Completion: Unpaired Point Cloud Completion using Cycle Transformation with Missing Region Codingcited by 50
  2. 2022Discover and Mitigate Unknown Biases with Debiasing Alternate Networkscited by 47
  3. 2021Style-based Point Generator with Adversarial Rendering for Point Cloud Completioncited by 45
  4. 20223D Shape Reconstruction from 2D Images with Disentangled Attribute Flowcited by 45
  5. 2022Comprehensive Review of Deep Learning-Based 3D Point Cloud Completion Processing and Analysiscited by 44
  6. 2022PointAttN: You Only Need Attention for Point Cloud Completioncited by 44
  7. 2023ProxyFormer: Proxy Alignment Assisted Point Cloud Completion with Missing Part Sensitive Transformercited by 43
  8. 2022Snowflake Point Deconvolution for Point Cloud Completion and Generation with Skip-Transformercited by 38
  9. 2023SVDFormer: Complementing Point Cloud via Self-view Augmentation and Self-structure Dual-generatorcited by 34
  10. 2021Voxel-based Network for Shape Completion by Leveraging Edge Generationcited by 32
  11. 2021ASFM-Net: Asymmetrical Siamese Feature Matching Network for Point Completioncited by 28
  12. 2022CSDN: Cross-modal Shape-transfer Dual-refinement Network for Point Cloud Completioncited by 22
  13. 2024CRA-PCN: Point Cloud Completion with Intra- and Inter-level Cross-Resolution Transformerscited by 21
  14. 2022Point Scene Understanding via Disentangled Instance Mesh Reconstructioncited by 20
  15. 2022FBNet: Feedback Network for Point Cloud Completioncited by 20
  16. 2021ME-PCN: Point Completion Conditioned on Mask Emptinesscited by 18
  17. 20223D-OAE: Occlusion Auto-Encoders for Self-Supervised Learning on Point Cloudscited by 18
  18. 2021Denoise and Contrast for Category Agnostic Shape Completioncited by 17
  19. 2022Learning a Structured Latent Space for Unsupervised Point Cloud Completioncited by 17
  20. 2022Revealing Occlusions with 4D Neural Fieldscited by 17
  21. 2021Self-Supervised Point Cloud Completion via Inpaintingcited by 16
  22. 2022Learning Local Displacements for Point Cloud Completioncited by 16
  23. 2025SymmCompletion: High-Fidelity and High-Consistency Point Cloud Completion with Symmetry Guidancecited by 15
  24. 2022Point Cloud Upsampling via Cascaded Refinement Networkcited by 14
  25. 2021KTNet: Knowledge Transfer for Unpaired 3D Shape Completioncited by 9
  26. 2021Multi-View Partial (MVP) Point Cloud Challenge 2021 on Completion and Registration: Methods and Resultscited by 9
  27. 2022CP3: Unifying Point Cloud Completion by Pretrain-Prompt-Predict Paradigmcited by 9
  28. 2022PointCA: Evaluating the Robustness of 3D Point Cloud Completion Models Against Adversarial Examplescited by 9
  29. 2023ACL-SPC: Adaptive Closed-Loop system for Self-Supervised Point Cloud Completioncited by 9
  30. 2023SCoDA: Domain Adaptive Shape Completion for Real Scanscited by 9
  31. 2024Explicitly Guided Information Interaction Network for Cross-modal Point Cloud Completioncited by 9
  32. 2025GenPC: Zero-shot Point Cloud Completion via 3D Generative Priorscited by 9
  33. 2021Attention-based Transformation from Latent Features to Point Cloudscited by 8
  34. 2023SCARP: 3D Shape Completion in ARbitrary Poses for Improved Graspingcited by 8
  35. 20243DMambaComplete: Exploring Structured State Space Model for Point Cloud Completioncited by 8
  36. 2022PatchRD: Detail-Preserving Shape Completion by Learning Patch Retrieval and Deformationcited by 7
  37. 2024T-CorresNet: Template Guided 3D Point Cloud Completion with Correspondence Pooling Query Generation Strategycited by 7
  38. 2024GeoFormer: Learning Point Cloud Completion with Tri-Plane Integrated Transformercited by 7

50 most cited of 112 All 112 (JSON)