mlsanityData to 7 Oct 2026

TetGAN: A Convolutional Neural Network for Tetrahedral Mesh Generation

arXiv 2210.05735 ↗First posted 11 Oct 2022cs.CV cs.GR cs.LGcited by 8

Not on the map. Why?

Abstract (arXiv)

We present TetGAN, a convolutional neural network designed to generate tetrahedral meshes. We represent shapes using an irregular tetrahedral grid which encodes an occupancy and displacement field. Our formulation enables defining tetrahedral convolution, pooling, and upsampling operations to synthesize explicit mesh connectivity with variable topological genus. The proposed neural network layers learn deep features over each tetrahedron and learn to extract patterns within spatial regions across multiple scales. We illustrate the capabilities of our technique to encode tetrahedral meshes into a semantically meaningful latent-space which can be used for shape editing and synthesis. Our project page is at https://threedle.github.io/tetGAN/.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 35 of its 55 references that are in the map. First posted on arXiv 11 Oct 2022.

Builds on

35 of 55 references.

References · 35

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  3. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  4. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,229
  5. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  6. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  7. 2017Improved Training of Wasserstein GANscited by 2,223
  8. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  9. 2021Alias-Free Generative Adversarial Networkscited by 1,181
  10. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  11. 2018Pixel2Mesh: Generating 3D Mesh Models from Single RGB Imagescited by 649
  12. 2016Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modelingcited by 558
23 more
  1. 2018AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generationcited by 539
  2. 2021Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesiscited by 459
  3. 2021Extracting Triangular 3D Models, Materials, and Lighting From Imagescited by 363
  4. 2020PolyGen: An Autoregressive Generative Model of 3D Meshescited by 267
  5. 2019BSP-Net: Generating Compact Meshes via Binary Space Partitioningcited by 205
  6. 2016Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networkscited by 192
  7. 2021Shape As Points: A Differentiable Poisson Solvercited by 186
  8. 2016Learning Shape Abstractions by Assembling Volumetric Primitivescited by 181
  9. 2019SDM-NET: Deep Generative Network for Structured Deformable Meshcited by 113
  10. 2021Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networkscited by 101
  11. 2021gradSim: Differentiable simulation for system identification and visuomotor controlcited by 100
  12. 2020Learning Deformable Tetrahedral Meshes for 3D Reconstructioncited by 84
  13. 2021Subdivision-Based Mesh Convolution Networkscited by 60
  14. 2018Robust Watertight Manifold Surface Generation Method for ShapeNet Modelscited by 58
  15. 2020Deep Geometric Texture Synthesiscited by 51
  16. 2020Neural Subdivisioncited by 49
  17. 2020Adversarial Generation of Continuous Implicit Shape Representationscited by 46
  18. 2020DECOR-GAN: 3D Shape Detailization by Conditional Refinementcited by 45
  19. 2020Primal-Dual Mesh Convolutional Neural Networkscited by 44
  20. 2019Fast Tetrahedral Meshing in the Wildcited by 35
  21. 2020PointTriNet: Learned Triangulation of 3D Point Setscited by 32
  22. 2020COALESCE: Component Assembly by Learning to Synthesize Connectionscited by 30
  23. 2021Differentiable Surface Triangulationcited by 14

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 4; 2024: 1; 2025: 1.

8 papers.

  1. 2023MeshDiffusion: Score-based Generative 3D Mesh Modelingcited by 198
  2. 2023Ghost on the Shell: An Expressive Representation of General 3D Shapescited by 24
  3. 2024TetSphere Splatting: Representing High-Quality Geometry with Lagrangian Volumetric Meshescited by 20
  4. 2025Eval3D: Interpretable and Fine-grained Evaluation for 3D Generationcited by 15
  5. 2022TetraDiffusion: Tetrahedral Diffusion Models for 3D Shape Generationcited by 14
  6. 2023Efficient Text-Guided 3D-Aware Portrait Generation with Score Distillation Sampling on Distributioncited by 4
  7. 2023Efficient Meshy Neural Fields for Animatable Human Avatarscited by 2
  8. 2022LoopDraw: a Loop-Based Autoregressive Model for Shape Synthesis and Editingcited by 1