mlsanityData to 7 Oct 2026

ASFM-Net: Asymmetrical Siamese Feature Matching Network for Point Completion

arXiv 2104.09587 ↗First posted 19 Apr 2021cs.CVcited by 28

Not on the map. Why?

Abstract (arXiv)

We tackle the problem of object completion from point clouds and propose a novel point cloud completion network employing an Asymmetrical Siamese Feature Matching strategy, termed as ASFM-Net. Specifically, the Siamese auto-encoder neural network is adopted to map the partial and complete input point cloud into a shared latent space, which can capture detailed shape prior. Then we design an iterative refinement unit to generate complete shapes with fine-grained details by integrating prior information. Experiments are conducted on the PCN dataset and the Completion3D benchmark, demonstrating the state-of-the-art performance of the proposed ASFM-Net. Our method achieves the 1st place in the leaderboard of Completion3D and outperforms existing methods with a large margin, about 12%. The codes and trained models are released publicly at https://github.com/Yan-Xia/ASFM-Net.

Key facts. Cited by 28 papers in the map (data through 7 Oct 2026). Builds on 30 of its 66 references that are in the map. First posted on arXiv 19 Apr 2021.

Builds on

30 of 66 references.

References · 30

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  3. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  4. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  5. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,275
  6. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  7. 2018Pixel2Mesh: Generating 3D Mesh Models from Single RGB Imagescited by 649
  8. 2018AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generationcited by 539
  9. 2018Hypergraph Neural Networkscited by 482
  10. 2016Semantic Scene Completion from a Single Depth Imagecited by 468
  11. 2018PCN: Point Completion Networkcited by 382
  12. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
18 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. 2020GRNet: Gridding Residual Network for Dense Point Cloud Completioncited by 174
  4. 2020PF-Net: Point Fractal Network for 3D Point Cloud Completioncited by 146
  5. 2020Cascaded Refinement Network for Point Cloud Completioncited by 112
  6. 2020Point Cloud Completion by Skip-attention Network with Hierarchical Foldingcited by 106
  7. 2016Shape Completion Enabled Robotic Graspingcited by 79
  8. 2020Detail Preserved Point Cloud Completion via Separated Feature Aggregationcited by 70
  9. 2018Triplet-Center Loss for Multi-View 3D Object Retrievalcited by 69
  10. 2020SOE-Net: A Self-Attention and Orientation Encoding Network for Point Cloud based Place Recognitioncited by 66
  11. 2019RL-GAN-Net: A Reinforcement Learning Agent Controlled GAN Network for Real-Time Point Cloud Shape Completioncited by 58
  12. 2016VConv-DAE: Deep Volumetric Shape Learning Without Object Labelscited by 50
  13. 2017Deformable Shape Completion with Graph Convolutional Autoencoderscited by 50
  14. 2020SoftPoolNet: Shape Descriptor for Point Cloud Completion and Classificationcited by 33
  15. 2019LCD: Learned Cross-Domain Descriptors for 2D-3D Matchingcited by 29
  16. 2020Point Set Voting for Partial Point Cloud Analysiscited by 22
  17. 2020VPC-Net: Completion of 3D Vehicles from MLS Point Cloudscited by 11
  18. 2018High Fidelity Semantic Shape Completion for Point Clouds using Latent Optimizationcited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 12; 2023: 2; 2024: 7; 2025: 3; 2026: 1.

28 papers.

Sort:

By area:

  1. 2021A Conditional Point Diffusion-Refinement Paradigm for 3D Point Cloud Completioncited by 100
  2. 2022SeedFormer: Patch Seeds based Point Cloud Completion with Upsample Transformercited by 83
  3. 2022Comprehensive Review of Deep Learning-Based 3D Point Cloud Completion Processing and Analysiscited by 44
  4. 2023ProxyFormer: Proxy Alignment Assisted Point Cloud Completion with Missing Part Sensitive Transformercited by 43
  5. 2022Snowflake Point Deconvolution for Point Cloud Completion and Generation with Skip-Transformercited by 38
  6. 2022LAKe-Net: Topology-Aware Point Cloud Completion by Localizing Aligned Keypointscited by 27
  7. 2022A Lightweight and Detector-free 3D Single Object Tracker on Point Cloudscited by 23
  8. 2022CASSPR: Cross Attention Single Scan Place Recognitioncited by 22
  9. 2022Learning Local Displacements for Point Cloud Completioncited by 16
  10. 2022CasFusionNet: A Cascaded Network for Point Cloud Semantic Scene Completion by Dense Feature Fusioncited by 11
  11. 2021KTNet: Knowledge Transfer for Unpaired 3D Shape Completioncited by 9
  12. 20243DMambaComplete: Exploring Structured State Space Model for Point Cloud Completioncited by 8
16 more
  1. 2024FSC: Few-point Shape Completioncited by 6
  2. 2021Multimodal Shape Completion via IMLEcited by 5
  3. 2022Temporal Point Cloud Completion with Pose Disturbancecited by 5
  4. 2022Shape Completion with Points in the Shadowcited by 4
  5. 2024Deep Learning for 3D Point Cloud Enhancement: A Surveycited by 4
  6. 2023SCP: Scene Completion Pre-training for 3D Object Detectioncited by 3
  7. 2022Point cloud completion via structured feature maps using a feedback networkcited by 2
  8. 2024Rethinking Data Input for Point Cloud Upsamplingcited by 2
  9. 2024Local Occupancy-Enhanced Object Grasping with Multiple Triplanar Projectioncited by 2
  10. 2022PCKRF: Point Cloud Completion and Keypoint Refinement With Fusion Data for 6D Pose Estimationcited by 1
  11. 2024Unsupervised Point Cloud Completion through Unbalanced Optimal Transportcited by 1
  12. 2025Representation Learning of Point Cloud Upsampling in Global and Local Inputscited by 1
  13. 2026SplAttN: Bridging 2D and 3D with Gaussian Soft Splatting and Attention for Point Cloud Completioncited by 1
  14. 2024Gap Completion in Point Cloud Scene occluded by Vehicles using SGC-Netcited by 0
  15. 2025Med-PU: Point Cloud Upsampling for High-Fidelity 3D Medical Shape Reconstructioncited by 0
  16. 2025Multi-modal Multi-task Pre-training for Improved Point Cloud Understandingcited by 0