mlsanityData to 7 Oct 2026

High-Fidelity Point Cloud Completion with Low-Resolution Recovery and Noise-Aware Upsampling

arXiv 2112.11271 ↗First posted 21 Dec 2021cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

Completing an unordered partial point cloud is a challenging task. Existing approaches that rely on decoding a latent feature to recover the complete shape, often lead to the completed point cloud being over-smoothing, losing details, and noisy. Instead of decoding a whole shape, we propose to decode and refine a low-resolution (low-res) point cloud first, and then performs a patch-wise noise-aware upsampling rather than interpolating the whole sparse point cloud at once, which tends to lose details. Regarding the possibility of lacking details of the initially decoded low-res point cloud, we propose an iterative refinement to recover the geometric details and a symmetrization process to preserve the trustworthy information from the input partial point cloud. After obtaining a sparse and complete point cloud, we propose a patch-wise upsampling strategy. Patch-based upsampling allows to better recover fine details unlike decoding a whole shape, however, the existing upsampling methods are not applicable to completion task due to the data discrepancy (i.e., input sparse data here is not from ground-truth). Therefore, we propose a patch extraction approach to generate training patch pairs between the sparse and ground-truth point clouds, and an outlier removal step to suppress the noisy points from the sparse point cloud. Together with the low-res recovery, our whole method is able to achieve high-fidelity point cloud completion. Comprehensive evaluations are provided to demonstrate the effectiveness of the proposed method and its individual components.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 40 of its 57 references that are in the map. First posted on arXiv 21 Dec 2021.

Builds on

40 of 57 references.

References · 40

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  4. 2013Auto-Encoding Variational Bayescited by 3,980
  5. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  6. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  7. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  8. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  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. 2018AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generationcited by 539
  12. 2019PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flowscited by 487
28 more
  1. 2018PCN: Point Completion Networkcited by 382
  2. 2020Implicit Functions in Feature Space for 3D Shape Reconstruction and Completioncited by 343
  3. 2020Learning Gradient Fields for Shape Generationcited by 245
  4. 2016Shape Completion using 3D-Encoder-Predictor CNNs and Shape Synthesiscited by 219
  5. 2018SO-Net: Self-Organizing Network for Point Cloud Analysiscited by 210
  6. 2018PU-Net: Point Cloud Upsampling Networkcited by 208
  7. 2020GRNet: Gridding Residual Network for Dense Point Cloud Completioncited by 174
  8. 2019PU-GAN: a Point Cloud Upsampling Adversarial Networkcited by 162
  9. 2020PF-Net: Point Fractal Network for 3D Point Cloud Completioncited by 146
  10. 2019Morphing and Sampling Network for Dense Point Cloud Completioncited by 132
  11. 2020Cascaded Refinement Network for Point Cloud Completioncited by 112
  12. 20183D Point Capsule Networkscited by 106
  13. 2020Point Cloud Completion by Skip-attention Network with Hierarchical Foldingcited by 106
  14. 2018Patch-based Progressive 3D Point Set Upsamplingcited by 101
  15. 2020PMP-Net: Point Cloud Completion by Learning Multi-step Point Moving Pathscited by 97
  16. 2019Unsupervised Multi-Task Feature Learning on Point Cloudscited by 89
  17. 2017High-Resolution Shape Completion Using Deep Neural Networks for Global Structure and Local Geometry Inferencecited by 87
  18. 2018EC-Net: an Edge-aware Point set Consolidation Networkcited by 84
  19. 2021Point Cloud Upsampling via Disentangled Refinementcited by 74
  20. 2020Detail Preserved Point Cloud Completion via Separated Feature Aggregationcited by 70
  21. 2018VV-Net: Voxel VAE Net with Group Convolutions for Point Cloud Segmentationcited by 64
  22. 2019RL-GAN-Net: A Reinforcement Learning Agent Controlled GAN Network for Real-Time Point Cloud Shape Completioncited by 58
  23. 2018Learning 3D Shape Completion under Weak Supervisioncited by 40
  24. 2020SoftPoolNet: Shape Descriptor for Point Cloud Completion and Classificationcited by 33
  25. 2020Skeleton-bridged Point Completion: From Global Inference to Local Adjustmentcited by 23
  26. 2019PRS-Net: Planar Reflective Symmetry Detection Net for 3D Modelscited by 20
  27. 2019A Convolutional Decoder for Point Clouds using Adaptive Instance Normalizationcited by 8
  28. 2018Deep RBFNet: Point Cloud Feature Learning using Radial Basis Functionscited by 7

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 0; 2024: 1; 2025: 1.

3 papers.

  1. 2022Comprehensive Review of Deep Learning-Based 3D Point Cloud Completion Processing and Analysiscited by 44
  2. 2024Hyperbolic Chamfer Distance for Point Cloud Completion and Beyondcited by 3
  3. 2025Denoising-While-Completing Network (DWCNet): Robust Point Cloud Completion Under Corruptioncited by 0