mlsanityData to 14 Oct 2026

Point Cloud Generation with Continuous Conditioning

arXiv 2202.08526 ↗First posted 17 Feb 2022cs.CV cs.AI cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

Generative models can be used to synthesize 3D objects of high quality and diversity. However, there is typically no control over the properties of the generated object.This paper proposes a novel generative adversarial network (GAN) setup that generates 3D point cloud shapes conditioned on a continuous parameter. In an exemplary application, we use this to guide the generative process to create a 3D object with a custom-fit shape. We formulate this generation process in a multi-task setting by using the concept of auxiliary classifier GANs. Further, we propose to sample the generator label input for training from a kernel density estimation (KDE) of the dataset. Our ablations show that this leads to significant performance increase in regions with few samples. Extensive quantitative and qualitative experiments show that we gain explicit control over the object dimensions while maintaining good generation quality and diversity.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 43 of its 55 references that are in the map. First posted on arXiv 17 Feb 2022.

Builds on

43 of 55 references.

References · 43

  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. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  4. 2013Auto-Encoding Variational Bayescited by 4,053
  5. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
  6. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  7. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  8. 2017Improved Training of Wasserstein GANscited by 2,235
  9. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  10. 2014Conditional Generative Adversarial Netscited by 2,162
  11. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
  12. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,715
31 more
  1. 2017Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semanticscited by 1,358
  2. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  3. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,205
  4. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,082
  5. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  6. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 979
  7. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  8. 2021Diffusion Probabilistic Models for 3D Point Cloud Generationcited by 735
  9. 2020PCT: Point cloud transformercited by 732
  10. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 657
  11. 2017Wasserstein GANcited by 639
  12. 2020GANSpace: Discovering Interpretable GAN Controlscited by 614
  13. 2016Conditional Image Synthesis With Auxiliary Classifier GANscited by 565
  14. 2016Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modelingcited by 558
  15. 2019PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flowscited by 488
  16. 2018cGANs with Projection Discriminatorcited by 254
  17. 2017AttGAN: Facial Attribute Editing by Only Changing What You Wantcited by 242
  18. 2018FlowNet3D: Learning Scene Flow in 3D Point Cloudscited by 242
  19. 20193D Point Cloud Generative Adversarial Network Based on Tree Structured Graph Convolutionscited by 173
  20. 2018Text2Shape: Generating Shapes from Natural Language by Learning Joint Embeddingscited by 169
  21. 2016Unsupervised Cross-Domain Image Generationcited by 125
  22. 2016Invertible Conditional GANs for image editingcited by 118
  23. 2018PointGrow: Autoregressively Learned Point Cloud Generation with Self-Attentioncited by 105
  24. 2021GAN-Control: Explicitly Controllable GANscited by 91
  25. 2021EfficientLPS: Efficient LiDAR Panoptic Segmentationcited by 76
  26. 2019Deep Level Sets: Implicit Surface Representations for 3D Shape Inferencecited by 53
  27. 2017Contextual-based Image Inpainting: Infer, Match, and Translatecited by 50
  28. 2015Text to 3D Scene Generation with Rich Lexical Groundingcited by 36
  29. 2020PT2PC: Learning to Generate 3D Point Cloud Shapes from Part Tree Conditionscited by 20
  30. 2019Quality-aware Unpaired Image-to-Image Translationcited by 9
  31. 2020Rethinking Sampling in 3D Point Cloud Generative Adversarial Networkscited by 7

Built on by

Cited by year (2026 to 14 Oct)

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

4 papers.

  1. 2024CCDM: Continuous Conditional Diffusion Models for Image Generationcited by 8
  2. 2023Turning Waste into Wealth: Leveraging Low-Quality Samples for Enhancing Continuous Conditional Generative Adversarial Networkscited by 3
  3. 2025Imbalance-Robust and Sampling-Efficient Continuous Conditional GANs via Adaptive Vicinal Learning and Auxiliary Regularizationcited by 0
  4. 2026Enhancing Diffusion-Based Quantitatively Controllable Image Generation via Matrix-Form EDM and Adaptive Vicinal Trainingcited by 0