mlsanityData to 7 Oct 2026

SnowflakeNet: Point Cloud Completion by Snowflake Point Deconvolution with Skip-Transformer

arXiv 2108.04444 ↗First posted 10 Aug 2021cs.CVcited by 162

Not on the map. Why?

Abstract (arXiv)

Point cloud completion aims to predict a complete shape in high accuracy from its partial observation. However, previous methods usually suffered from discrete nature of point cloud and unstructured prediction of points in local regions, which makes it hard to reveal fine local geometric details on the complete shape. To resolve this issue, we propose SnowflakeNet with Snowflake Point Deconvolution (SPD) to generate the complete point clouds. The SnowflakeNet models the generation of complete point clouds as the snowflake-like growth of points in 3D space, where the child points are progressively generated by splitting their parent points after each SPD. Our insight of revealing detailed geometry is to introduce skip-transformer in SPD to learn point splitting patterns which can fit local regions the best. Skip-transformer leverages attention mechanism to summarize the splitting patterns used in the previous SPD layer to produce the splitting in the current SPD layer. The locally compact and structured point cloud generated by SPD is able to precisely capture the structure characteristic of 3D shape in local patches, which enables the network to predict highly detailed geometries, such as smooth regions, sharp edges and corners. Our experimental results outperform the state-of-the-art point cloud completion methods under widely used benchmarks. Code will be available at https://github.com/AllenXiangX/SnowflakeNet.

Key facts. Cited by 162 papers in the map (data through 7 Oct 2026). Builds on 47 of its 60 references that are in the map. First posted on arXiv 10 Aug 2021.

Builds on

47 of 60 references.

References · 47

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  4. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  5. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  6. 2020Point Transformercited by 1,462
  7. 2018Image Transformercited by 770
  8. 2020PCT: Point cloud transformercited by 730
  9. 2018AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generationcited by 539
  10. 2018PCN: Point Completion Networkcited by 382
  11. 2016Shape Completion using 3D-Encoder-Predictor CNNs and Shape Synthesiscited by 219
  12. 2018PU-Net: Point Cloud Upsampling Networkcited by 208
35 more
  1. 20203D Object Detection with Pointformercited by 194
  2. 2020GRNet: Gridding Residual Network for Dense Point Cloud Completioncited by 174
  3. 2019PU-GAN: a Point Cloud Upsampling Adversarial Networkcited by 162
  4. 2019SDFDiff: Differentiable Rendering of Signed Distance Fields for 3D Shape Optimizationcited by 159
  5. 2020PF-Net: Point Fractal Network for 3D Point Cloud Completioncited by 146
  6. 2020Neural-Pull: Learning Signed Distance Functions from Point Clouds by Learning to Pull Space onto Surfacescited by 146
  7. 2019Morphing and Sampling Network for Dense Point Cloud Completioncited by 132
  8. 2020Cascaded Refinement Network for Point Cloud Completioncited by 112
  9. 2020Point Cloud Completion by Skip-attention Network with Hierarchical Foldingcited by 106
  10. 2018Point2Sequence: Learning the Shape Representation of 3D Point Clouds with an Attention-based Sequence to Sequence Networkcited by 100
  11. 2020PMP-Net: Point Cloud Completion by Learning Multi-step Point Moving Pathscited by 97
  12. 2020Detail Preserved Point Cloud Completion via Separated Feature Aggregationcited by 70
  13. 2019Unpaired Point Cloud Completion on Real Scans using Adversarial Trainingcited by 66
  14. 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
  15. 2021Cycle4Completion: Unpaired Point Cloud Completion using Cycle Transformation with Missing Region Codingcited by 50
  16. 2018View Inter-Prediction GAN: Unsupervised Representation Learning for 3D Shapes by Learning Global Shape Memories to Support Local View Predictionscited by 43
  17. 2020DRWR: A Differentiable Renderer without Rendering for Unsupervised 3D Structure Learning from Silhouette Imagescited by 35
  18. 2020SoftPoolNet: Shape Descriptor for Point Cloud Completion and Classificationcited by 33
  19. 2020Weakly-supervised 3D Shape Completion in the Wildcited by 33
  20. 2019L2G Auto-encoder: Understanding Point Clouds by Local-to-Global Reconstruction with Hierarchical Self-Attentioncited by 32
  21. 2019ShapeCaptioner: Generative Caption Network for 3D Shapes by Learning a Mapping from Parts Detected in Multiple Views to Sentencescited by 30
  22. 2020Fine-Grained 3D Shape Classification with Hierarchical Part-View Attentionscited by 30
  23. 2018Y^2Seq2Seq: Cross-Modal Representation Learning for 3D Shape and Text by Joint Reconstruction and Prediction of View and Word Sequencescited by 26
  24. 2020Skeleton-bridged Point Completion: From Global Inference to Local Adjustmentcited by 23
  25. 2019Render4Completion: Synthesizing Multi-View Depth Maps for 3D Shape Completioncited by 22
  26. 20193D Shape Completion with Multi-view Consistent Inferencecited by 22
  27. 2020Point Set Voting for Partial Point Cloud Analysiscited by 22
  28. 2020SeqXY2SeqZ: Structure Learning for 3D Shapes by Sequentially Predicting 1D Occupancy Segments From 2D Coordinatescited by 17
  29. 2019Point2SpatialCapsule: Aggregating Features and Spatial Relationships of Local Regions on Point Clouds using Spatial-aware Capsulescited by 14
  30. 2018Local Frequency Interpretation and Non-Local Self-Similarity on Graph for Point Cloud Inpaintingcited by 13
  31. 20193DViewGraph: Learning Global Features for 3D Shapes from A Graph of Unordered Views with Attentioncited by 12
  32. 2019Parts4Feature: Learning 3D Global Features from Generally Semantic Parts in Multiple Viewscited by 10
  33. 2020LRC-Net: Learning Discriminative Features on Point Clouds by Encoding Local Region Contextscited by 10
  34. 2021Hierarchical View Predictor: Unsupervised 3D Global Feature Learning through Hierarchical Prediction among Unordered Viewscited by 7
  35. 2019Adversarial Cross-Modal Retrieval via Learning and Transferring Single-Modal Similaritiescited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 35; 2023: 32; 2024: 36; 2025: 32; 2026: 22.

162 papers.

Sort:

By area:

  1. 2023Triplane Meets Gaussian Splatting: Fast and Generalizable Single-View 3D Reconstruction with Transformerscited by 257
  2. 2021A Survey of Visual Transformerscited by 117
  3. 2022ShapeFormer: Transformer-based Shape Completion via Sparse Representationcited by 106
  4. 2022SeedFormer: Patch Seeds based Point Cloud Completion with Upsample Transformercited by 83
  5. 2023AdaPoinTr: Diverse Point Cloud Completion with Adaptive Geometry-Aware Transformerscited by 65
  6. 2022Reconstructing Surfaces for Sparse Point Clouds with On-Surface Priorscited by 60
  7. 2022Surface Reconstruction from Point Clouds by Learning Predictive Context Priorscited by 54
  8. 2022Implicit Autoencoder for Point-Cloud Self-Supervised Representation Learningcited by 46
  9. 20223D Shape Reconstruction from 2D Images with Disentangled Attribute Flowcited by 45
  10. 2022Low-Rank Tensor Function Representation for Multi-Dimensional Data Recoverycited by 45
  11. 2022Comprehensive Review of Deep Learning-Based 3D Point Cloud Completion Processing and Analysiscited by 44
  12. 2022PointAttN: You Only Need Attention for Point Cloud Completioncited by 43
38 more
  1. 2023ProxyFormer: Proxy Alignment Assisted Point Cloud Completion with Missing Part Sensitive Transformercited by 43
  2. 2021PVT: Point-Voxel Transformer for Point Cloud Learningcited by 42
  3. 2022Learning Deep Implicit Functions for 3D Shapes with Dynamic Code Cloudscited by 42
  4. 2022Autoregressive 3D Shape Generation via Canonical Mappingcited by 37
  5. 2023Point-Cloud Completion with Pretrained Text-to-image Diffusion Modelscited by 37
  6. 2022Cross-modal Learning for Image-Guided Point Cloud Shape Completioncited by 36
  7. 2023Learning a More Continuous Zero Level Set in Unsigned Distance Fields through Level Set Projectioncited by 36
  8. 2023SVDFormer: Complementing Point Cloud via Self-view Augmentation and Self-structure Dual-generatorcited by 34
  9. 2022Transformers in 3D Point Clouds: A Surveycited by 31
  10. 2023Unsupervised Inference of Signed Distance Functions from Single Sparse Point Clouds without Learning Priorscited by 28
  11. 2022LAKe-Net: Topology-Aware Point Cloud Completion by Localizing Aligned Keypointscited by 27
  12. 2023Learning Signed Distance Functions from Noisy 3D Point Clouds via Noise to Noise Mappingcited by 27
  13. 2022CSDN: Cross-modal Shape-transfer Dual-refinement Network for Point Cloud Completioncited by 22
  14. 2022Latent Partition Implicit with Surface Codes for 3D Representationcited by 21
  15. 20223D Vision with Transformers: A Surveycited by 21
  16. 2024CRA-PCN: Point Cloud Completion with Intra- and Inter-level Cross-Resolution Transformerscited by 21
  17. 2022FBNet: Feedback Network for Point Cloud Completioncited by 20
  18. 2023P2C: Self-Supervised Point Cloud Completion from Single Partial Cloudscited by 19
  19. 20223D-OAE: Occlusion Auto-Encoders for Self-Supervised Learning on Point Cloudscited by 18
  20. 2024Generative Densification: Learning to Densify Gaussians for High-Fidelity Generalizable 3D Reconstructioncited by 18
  21. 2022Learning a Structured Latent Space for Unsupervised Point Cloud Completioncited by 17
  22. 2024PCDreamer: Point Cloud Completion Through Multi-view Diffusion Priorscited by 16
  23. 2021Deep Point Cloud Reconstructioncited by 15
  24. 2024Fast Learning of Signed Distance Functions from Noisy Point Clouds via Noise to Noise Mappingcited by 15
  25. 2025SymmCompletion: High-Fidelity and High-Consistency Point Cloud Completion with Symmetry Guidancecited by 15
  26. 2022Point Cloud Upsampling via Cascaded Refinement Networkcited by 14
  27. 2022Sparse2Dense: Learning to Densify 3D Features for 3D Object Detectioncited by 14
  28. 2023PointSSC: A Cooperative Vehicle-Infrastructure Point Cloud Benchmark for Semantic Scene Completioncited by 13
  29. 2022MM-3DScene: 3D Scene Understanding by Customizing Masked Modeling with Informative-Preserved Reconstruction and Self-Distilled Consistencycited by 12
  30. 2025RoGSplat: Learning Robust Generalizable Human Gaussian Splatting from Sparse Multi-View Imagescited by 12
  31. 2023GridPull: Towards Scalability in Learning Implicit Representations from 3D Point Cloudscited by 11
  32. 2025HORT: Monocular Hand-held Objects Reconstruction with Transformerscited by 11
  33. 2024Large Point-to-Gaussian Model for Image-to-3D Generationcited by 10
  34. 2021KTNet: Knowledge Transfer for Unpaired 3D Shape Completioncited by 9
  35. 2021Multi-View Partial (MVP) Point Cloud Challenge 2021 on Completion and Registration: Methods and Resultscited by 9
  36. 2022CP3: Unifying Point Cloud Completion by Pretrain-Prompt-Predict Paradigmcited by 9
  37. 2022Energy-Based Residual Latent Transport for Unsupervised Point Cloud Completioncited by 9
  38. 2023ACL-SPC: Adaptive Closed-Loop system for Self-Supervised Point Cloud Completioncited by 9

50 most cited of 162 All 162 (JSON)