mlsanityData to 14 Oct 2026

KTNet: Knowledge Transfer for Unpaired 3D Shape Completion

arXiv 2111.11976 ↗First posted 23 Nov 2021cs.CVcited by 9

Not on the map. Why?

Abstract (arXiv)

Unpaired 3D object completion aims to predict a complete 3D shape from an incomplete input without knowing the correspondence between the complete and incomplete shapes. In this paper, we propose the novel KTNet to solve this task from the new perspective of knowledge transfer. KTNet elaborates a teacher-assistant-student network to establish multiple knowledge transfer processes. Specifically, the teacher network takes complete shape as input and learns the knowledge of complete shape. The student network takes the incomplete one as input and restores the corresponding complete shape. And the assistant modules not only help to transfer the knowledge of complete shape from the teacher to the student, but also judge the learning effect of the student network. As a result, KTNet makes use of a more comprehensive understanding to establish the geometric correspondence between complete and incomplete shapes in a perspective of knowledge transfer, which enables more detailed geometric inference for generating high-quality complete shapes. We conduct comprehensive experiments on several datasets, and the results show that our method outperforms previous methods of unpaired point cloud completion by a large margin.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 39 of its 62 references that are in the map. First posted on arXiv 23 Nov 2021.

Builds on

39 of 62 references.

References · 39

  1. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  4. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  5. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  6. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  7. 2017Matterport3D: Learning from RGB-D Data in Indoor Environmentscited by 1,376
  8. 2018PCN: Point Completion Networkcited by 384
  9. 2019Deep Closest Point: Learning Representations for Point Cloud Registrationcited by 321
  10. 2021PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformerscited by 286
  11. 2016Shape Completion using 3D-Encoder-Predictor CNNs and Shape Synthesiscited by 219
  12. 2020GRNet: Gridding Residual Network for Dense Point Cloud Completioncited by 174
27 more
  1. 2021SnowflakeNet: Point Cloud Completion by Snowflake Point Deconvolution with Skip-Transformercited by 164
  2. 2020PF-Net: Point Fractal Network for 3D Point Cloud Completioncited by 146
  3. 2019Morphing and Sampling Network for Dense Point Cloud Completioncited by 132
  4. 2020Cascaded Refinement Network for Point Cloud Completioncited by 112
  5. 2020Point Cloud Completion by Skip-attention Network with Hierarchical Foldingcited by 106
  6. 2021Variational Relational Point Completion Networkcited by 104
  7. 2020PMP-Net: Point Cloud Completion by Learning Multi-step Point Moving Pathscited by 97
  8. 2020Detail Preserved Point Cloud Completion via Separated Feature Aggregationcited by 70
  9. 2021Unsupervised 3D Shape Completion through GAN Inversioncited by 70
  10. 2021You Only Hypothesize Once: Point Cloud Registration with Rotation-equivariant Descriptorscited by 68
  11. 2019Unpaired Point Cloud Completion on Real Scans using Adversarial Trainingcited by 66
  12. 2019Multi-Angle Point Cloud-VAE: Unsupervised Feature Learning for 3D Point Clouds from Multiple Angles by Joint Self-Reconstruction and Half-to-Half Predictioncited by 66
  13. 2020Multimodal Shape Completion via Conditional Generative Adversarial Networkscited by 61
  14. 2018A LiDAR Point Cloud Generator: from a Virtual World to Autonomous Drivingcited by 54
  15. 2021Cycle4Completion: Unpaired Point Cloud Completion using Cycle Transformation with Missing Region Codingcited by 50
  16. 2021Style-based Point Generator with Adversarial Rendering for Point Cloud Completioncited by 45
  17. 2020PC-RGNN: Point Cloud Completion and Graph Neural Network for 3D Object Detectioncited by 35
  18. 2021Voxel-based Network for Shape Completion by Leveraging Edge Generationcited by 32
  19. 2021ASFM-Net: Asymmetrical Siamese Feature Matching Network for Point Completioncited by 28
  20. 20173D Object Reconstruction from a Single Depth View with Adversarial Learningcited by 26
  21. 2017Shape Inpainting using 3D Generative Adversarial Network and Recurrent Convolutional Networkscited by 23
  22. 2021ME-PCN: Point Completion Conditioned on Mask Emptinesscited by 18
  23. 2021Denoise and Contrast for Category Agnostic Shape Completioncited by 17
  24. 2018Local Frequency Interpretation and Non-Local Self-Similarity on Graph for Point Cloud Inpaintingcited by 13
  25. 2021PC2-PU: Patch Correlation and Point Correlation for Effective Point Cloud Upsamplingcited by 11
  26. 2020ChartPointFlow for Topology-Aware 3D Point Cloud Generationcited by 6
  27. 2020KAPLAN: A 3D Point Descriptor for Shape Completioncited by 2

Built on by

Cited by year (2026 to 14 Oct)

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

9 papers.

  1. 2024Explicitly Guided Information Interaction Network for Cross-modal Point Cloud Completioncited by 9
  2. 2024Unsupervised 3D Point Cloud Completion via Multi-view Adversarial Learningcited by 6
  3. 2023Diverse Shape Completion via Style Modulated Generative Adversarial Networkscited by 2
  4. 2026Denoise and Align: Towards Source-Free UDA for Robust Panoramic Semantic Segmentationcited by 1
  5. 2023Weakly Supervised Label Learning Flowscited by 0
  6. 2025INRet: A General Framework for Accurate Retrieval of INRs for Shapescited by 0
  7. 2025Empowering Bridge Digital Twins by Bridging the Data Gap with a Unified Synthesis Frameworkcited by 0
  8. 2025Dual-Model Weight Selection and Self-Knowledge Distillation for Medical Image Classificationcited by 0
  9. 2025TransBridge: Boost 3D Object Detection by Scene-Level Completion with Transformer Decodercited by 0