mlsanityData to 14 Oct 2026

Style-based Point Generator with Adversarial Rendering for Point Cloud Completion

arXiv 2103.02535 ↗First posted 3 Mar 2021cs.CVcited by 45

Not on the map. Why?

Abstract (arXiv)

In this paper, we proposed a novel Style-based Point Generator with Adversarial Rendering (SpareNet) for point cloud completion. Firstly, we present the channel-attentive EdgeConv to fully exploit the local structures as well as the global shape in point features. Secondly, we observe that the concatenation manner used by vanilla foldings limits its potential of generating a complex and faithful shape. Enlightened by the success of StyleGAN, we regard the shape feature as style code that modulates the normalization layers during the folding, which considerably enhances its capability. Thirdly, we realize that existing point supervisions, e.g., Chamfer Distance or Earth Mover's Distance, cannot faithfully reflect the perceptual quality of the reconstructed points. To address this, we propose to project the completed points to depth maps with a differentiable renderer and apply adversarial training to advocate the perceptual realism under different viewpoints. Comprehensive experiments on ShapeNet and KITTI prove the effectiveness of our method, which achieves state-of-the-art quantitative performance while offering superior visual quality.

Key facts. Cited by 45 papers in the map (data through 14 Oct 2026). Builds on 34 of its 43 references that are in the map. First posted on arXiv 3 Mar 2021.

Builds on

34 of 43 references.

References · 34

  1. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  3. 2017Squeeze-and-Excitation Networkscited by 4,789
  4. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  5. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  6. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  7. 2014Conditional Generative Adversarial Netscited by 2,162
  8. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,636
  9. 2017Deep Setscited by 1,421
  10. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,205
  11. 2016Least Squares Generative Adversarial Networkscited by 1,001
  12. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 979
22 more
  1. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  2. 2019Deep Learning for 3D Point Clouds: A Surveycited by 558
  3. 2018AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generationcited by 539
  4. 2018PCN: Point Completion Networkcited by 384
  5. 2019SynSin: End-to-end View Synthesis from a Single Imagecited by 364
  6. 2019Neural Point-Based Graphicscited by 327
  7. 2018SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filterscited by 261
  8. 2019Differentiable Surface Splatting for Point-based Geometry Processingcited by 239
  9. 2016Shape Completion using 3D-Encoder-Predictor CNNs and Shape Synthesiscited by 219
  10. 2020GRNet: Gridding Residual Network for Dense Point Cloud Completioncited by 174
  11. 20193D Point Cloud Generative Adversarial Network Based on Tree Structured Graph Convolutionscited by 173
  12. 2018Point Convolutional Neural Networks by Extension Operatorscited by 154
  13. 2020PF-Net: Point Fractal Network for 3D Point Cloud Completioncited by 146
  14. 2017Pointwise Convolutional Neural Networkscited by 127
  15. 2020Cascaded Refinement Network for Point Cloud Completioncited by 112
  16. 2020Point Cloud Completion by Skip-attention Network with Hierarchical Foldingcited by 106
  17. 2018Unsupervised Learning of Shape and Pose with Differentiable Point Cloudscited by 89
  18. 2018Local Spectral Graph Convolution for Point Set Feature Learningcited by 84
  19. 2020Detail Preserved Point Cloud Completion via Separated Feature Aggregationcited by 70
  20. 2019Unpaired Point Cloud Completion on Real Scans using Adversarial Trainingcited by 66
  21. 2019Neural Point Cloud Rendering via Multi-Plane Projectioncited by 60
  22. 2019Render4Completion: Synthesizing Multi-View Depth Maps for 3D Shape Completioncited by 22

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 7; 2022: 19; 2023: 5; 2024: 7; 2025: 3; 2026: 4.

45 papers.

Sort:

By area:

  1. 2022Rodin: A Generative Model for Sculpting 3D Digital Avatars Using Diffusioncited by 309
  2. 2023DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Priorcited by 158
  3. 2021Density-aware Chamfer Distance as a Comprehensive Metric for Point Cloud Completioncited by 112
  4. 2022SeedFormer: Patch Seeds based Point Cloud Completion with Upsample Transformercited by 83
  5. 2021Transfer Learning from Synthetic to Real LiDAR Point Cloud for Semantic Segmentationcited by 76
  6. 2022Unsupervised Point Cloud Representation Learning with Deep Neural Networks: A Surveycited by 54
  7. 2022Comprehensive Review of Deep Learning-Based 3D Point Cloud Completion Processing and Analysiscited by 44
  8. 2022PointAttN: You Only Need Attention for Point Cloud Completioncited by 44
  9. 2021Deep Implicit Surface Point Prediction Networkscited by 40
  10. 2022Snowflake Point Deconvolution for Point Cloud Completion and Generation with Skip-Transformercited by 38
  11. 2022Cross-modal Learning for Image-Guided Point Cloud Shape Completioncited by 36
  12. 2023SVDFormer: Complementing Point Cloud via Self-view Augmentation and Self-structure Dual-generatorcited by 34
33 more
  1. 2022LAKe-Net: Topology-Aware Point Cloud Completion by Localizing Aligned Keypointscited by 27
  2. 2022CSDN: Cross-modal Shape-transfer Dual-refinement Network for Point Cloud Completioncited by 22
  3. 20223DFaceShop: Explicitly Controllable 3D-Aware Portrait Generationcited by 22
  4. 2021ME-PCN: Point Completion Conditioned on Mask Emptinesscited by 18
  5. 2022Learning a Structured Latent Space for Unsupervised Point Cloud Completioncited by 17
  6. 2022Sparse2Dense: Learning to Densify 3D Features for 3D Object Detectioncited by 14
  7. 2021KTNet: Knowledge Transfer for Unpaired 3D Shape Completioncited by 9
  8. 2022PointCA: Evaluating the Robustness of 3D Point Cloud Completion Models Against Adversarial Examplescited by 9
  9. 2024DiffuX2CT: Diffusion Learning to Reconstruct CT Images from Biplanar X-Rayscited by 9
  10. 2025GenPC: Zero-shot Point Cloud Completion via 3D Generative Priorscited by 9
  11. 2026LaS-Comp: Zero-shot 3D Completion with Latent-Spatial Consistencycited by 9
  12. 2021Attention-based Transformation from Latent Features to Point Cloudscited by 8
  13. 2022PatchRD: Detail-Preserving Shape Completion by Learning Patch Retrieval and Deformationcited by 7
  14. 2024GeoFormer: Learning Point Cloud Completion with Tri-Plane Integrated Transformercited by 7
  15. 2024DreamCraft3D++: Efficient Hierarchical 3D Generation with Multi-Plane Reconstruction Modelcited by 7
  16. 2024FSC: Few-point Shape Completioncited by 6
  17. 2022Temporal Point Cloud Completion with Pose Disturbancecited by 5
  18. 2024Building-PCC: Building Point Cloud Completion Benchmarkscited by 5
  19. 2021Z2P: Instant Visualization of Point Cloudscited by 3
  20. 2022Point cloud completion via structured feature maps using a feedback networkcited by 2
  21. 2022SPA-VAE: Similar-Parts-Assignment for Unsupervised 3D Point Cloud Generationcited by 2
  22. 2022Completing Partial Point Clouds with Outliers by Collaborative Completion and Segmentationcited by 2
  23. 2023Diverse Shape Completion via Style Modulated Generative Adversarial Networkscited by 2
  24. 2024FreeCloth: Free-form Generation Enhances Challenging Clothed Human Modelingcited by 2
  25. 2026MGPC: Multimodal Network for Generalizable Point Cloud Completion With Modality Dropout and Progressive Decodingcited by 2
  26. 2022Deep Generative Models on 3D Representations: A Surveycited by 1
  27. 2024GANFusion: Feed-Forward Text-to-3D with Diffusion in GAN Spacecited by 1
  28. 2025CE-NPBG: Connectivity Enhanced Neural Point-Based Graphics for Novel View Synthesis in Autonomous Driving Scenescited by 1
  29. 2023StarNet: Style-Aware 3D Point Cloud Generationcited by 0
  30. 2023DualGenerator: Information Interaction-based Generative Network for Point Cloud Completioncited by 0
  31. 2025DT-NeRF: A Diffusion and Transformer-Based Optimization Approach for Neural Radiance Fields in 3D Reconstructioncited by 0
  32. 2026FS-I2P:A Hierarchical Focus-Sweep Registration Network with Dynamically Allocated Depthcited by 0
  33. 2026ProjFormer: Point Cloud Completion via Geometric-Projective Transformer and Cross-Modal Semantic Constraintscited by 0