mlsanityData to 14 Oct 2026

A Point Cloud Generative Model via Tree-Structured Graph Convolutions for 3D Brain Shape Reconstruction

arXiv 2107.09923 ↗First posted 21 Jul 2021eess.IV cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

Fusing medical images and the corresponding 3D shape representation can provide complementary information and microstructure details to improve the operational performance and accuracy in brain surgery. However, compared to the substantial image data, it is almost impossible to obtain the intraoperative 3D shape information by using physical methods such as sensor scanning, especially in minimally invasive surgery and robot-guided surgery. In this paper, a general generative adversarial network (GAN) architecture based on graph convolutional networks is proposed to reconstruct the 3D point clouds (PCs) of brains by using one single 2D image, thus relieving the limitation of acquiring 3D shape data during surgery. Specifically, a tree-structured generative mechanism is constructed to use the latent vector effectively and transfer features between hidden layers accurately. With the proposed generative model, a spontaneous image-to-PC conversion is finished in real-time. Competitive qualitative and quantitative experimental results have been achieved on our model. In multiple evaluation methods, the proposed model outperforms another common point cloud generative model PointOutNet.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 17 of its 41 references that are in the map. First posted on arXiv 21 Jul 2021.

Builds on

17 of 41 references.

References · 17

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  3. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  4. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  5. 2017Improved Training of Wasserstein GANscited by 2,235
  6. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,054
  7. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,694
  8. 2019Simplifying Graph Convolutional Networkscited by 1,477
  9. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  10. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 979
  11. 2018Pixel2Mesh: Generating 3D Mesh Models from Single RGB Imagescited by 651
  12. 2016Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modelingcited by 558
5 more
  1. 20193D Point Cloud Generative Adversarial Network Based on Tree Structured Graph Convolutionscited by 173
  2. 2016FPNN: Field Probing Neural Networks for 3D Datacited by 25
  3. 2020Tensorizing GAN with High-Order Pooling for Alzheimer's Disease Assessmentcited by 21
  4. 2019One-stage Shape Instantiation from a Single 2D Image to 3D Point Cloudcited by 9
  5. 2019Probabilistic Point Cloud Reconstructions for Vertebral Shape Analysiscited by 5

Built on by

Cited by year

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

8 papers.

  1. 20213D Brain Reconstruction by Hierarchical Shape-Perception Network from a Single Incomplete Imagecited by 10
  2. 2023Brain Structure-Function Fusing Representation Learning using Adversarial Decomposed-VAE for Analyzing MCIcited by 5
  3. 2025From Pixels to Polygons: A Survey of Deep Learning Approaches for Medical Image-to-Mesh Reconstructioncited by 4
  4. 2025A Survey of Medical Point Cloud Shape Learning: Registration, Reconstruction and Variationcited by 2
  5. 2022Dynamic Community Detection via Adversarial Temporal Graph Representation Learningcited by 0
  6. 2023SG-GAN: Fine Stereoscopic-Aware Generation for 3D Brain Point Cloud Up-sampling from a Single Imagecited by 0
  7. 2024A New Method in Facial Registration in Clinics Based on Structure Light Imagescited by 0
  8. 2025Med-PU: Point Cloud Upsampling for High-Fidelity 3D Medical Shape Reconstructioncited by 0