mlsanityData to 7 Oct 2026

SPCNet: Stepwise Point Cloud Completion Network

arXiv 2209.01746 ↗First posted 5 Sep 2022cs.CV cs.GRcited by 1

Not on the map. Why?

Abstract (arXiv)

How will you repair a physical object with large missings? You may first recover its global yet coarse shape and stepwise increase its local details. We are motivated to imitate the above physical repair procedure to address the point cloud completion task. We propose a novel stepwise point cloud completion network (SPCNet) for various 3D models with large missings. SPCNet has a hierarchical bottom-to-up network architecture. It fulfills shape completion in an iterative manner, which 1) first infers the global feature of the coarse result; 2) then infers the local feature with the aid of global feature; and 3) finally infers the detailed result with the help of local feature and coarse result. Beyond the wisdom of simulating the physical repair, we newly design a cycle loss %based training strategy to enhance the generalization and robustness of SPCNet. Extensive experiments clearly show the superiority of our SPCNet over the state-of-the-art methods on 3D point clouds with large missings.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 25 of its 54 references that are in the map. First posted on arXiv 5 Sep 2022.

Builds on

25 of 54 references.

References · 25

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  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. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  5. 2018PCN: Point Completion Networkcited by 382
  6. 2016Shape Completion using 3D-Encoder-Predictor CNNs and Shape Synthesiscited by 219
  7. 2020GRNet: Gridding Residual Network for Dense Point Cloud Completioncited by 174
  8. 2020PF-Net: Point Fractal Network for 3D Point Cloud Completioncited by 146
  9. 2017Learning Efficient Point Cloud Generation for Dense 3D Object Reconstructioncited by 133
  10. 2019Morphing and Sampling Network for Dense Point Cloud Completioncited by 132
  11. 2017Pointwise Convolutional Neural Networkscited by 126
  12. 2020Cascaded Refinement Network for Point Cloud Completioncited by 112
13 more
  1. 2021Variational Relational Point Completion Networkcited by 103
  2. 2018Point2Sequence: Learning the Shape Representation of 3D Point Clouds with an Attention-based Sequence to Sequence Networkcited by 100
  3. 2017High-Resolution Shape Completion Using Deep Neural Networks for Global Structure and Local Geometry Inferencecited by 87
  4. 2019Unpaired Point Cloud Completion on Real Scans using Adversarial Trainingcited by 66
  5. 2021Adaptive Graph Convolution for Point Cloud Analysiscited by 60
  6. 2019RL-GAN-Net: A Reinforcement Learning Agent Controlled GAN Network for Real-Time Point Cloud Shape Completioncited by 58
  7. 2019Spherical Kernel for Efficient Graph Convolution on 3D Point Cloudscited by 57
  8. 2021Cycle4Completion: Unpaired Point Cloud Completion using Cycle Transformation with Missing Region Codingcited by 50
  9. 2018View Inter-Prediction GAN: Unsupervised Representation Learning for 3D Shapes by Learning Global Shape Memories to Support Local View Predictionscited by 43
  10. 2019Render4Completion: Synthesizing Multi-View Depth Maps for 3D Shape Completioncited by 22
  11. 2018Local Frequency Interpretation and Non-Local Self-Similarity on Graph for Point Cloud Inpaintingcited by 13
  12. 20193DViewGraph: Learning Global Features for 3D Shapes from A Graph of Unordered Views with Attentioncited by 12
  13. 2019Parts4Feature: Learning 3D Global Features from Generally Semantic Parts in Multiple Viewscited by 10

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025PointSea: Point Cloud Completion via Self-structure Augmentationcited by 9