mlsanityData to 7 Oct 2026

Generative and Discriminative Voxel Modeling with Convolutional Neural Networks

arXiv 1608.04236 ↗First posted 15 Aug 2016cs.CV cs.HC cs.LGcited by 128

Not on the map. Why?

Abstract (arXiv)

When working with three-dimensional data, choice of representation is key. We explore voxel-based models, and present evidence for the viability of voxellated representations in applications including shape modeling and object classification. Our key contributions are methods for training voxel-based variational autoencoders, a user interface for exploring the latent space learned by the autoencoder, and a deep convolutional neural network architecture for object classification. We address challenges unique to voxel-based representations, and empirically evaluate our models on the ModelNet benchmark, where we demonstrate a 51.5% relative improvement in the state of the art for object classification.

Key facts. Cited by 128 papers in the map (data through 7 Oct 2026). First posted on arXiv 15 Aug 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 22; 2022: 36; 2023: 28; 2024: 21; 2025: 14; 2026: 7.

128 papers.

Sort:

By area:

  1. 20213D Shape Generation and Completion through Point-Voxel Diffusioncited by 516
  2. 2021Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesiscited by 459
  3. 20233DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Modelscited by 449
  4. 2022Rodin: A Generative Model for Sculpting 3D Digital Avatars Using Diffusioncited by 309
  5. 2023MeshGPT: Generating Triangle Meshes with Decoder-Only Transformerscited by 254
  6. 2023Michelangelo: Conditional 3D Shape Generation based on Shape-Image-Text Aligned Latent Representationcited by 225
  7. 2021Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networkscited by 101
  8. 2021Holistic 3D Scene Understanding from a Single Image with Implicit Representationcited by 94
  9. 2021ShaRF: Shape-conditioned Radiance Fields from a Single Viewcited by 92
  10. 2024Meshtron: High-Fidelity, Artist-Like 3D Mesh Generation at Scalecited by 87
  11. 2022Dual Octree Graph Networks for Learning Adaptive Volumetric Shape Representationscited by 71
  12. 2021Deep Implicit Moving Least-Squares Functions for 3D Reconstructioncited by 67
38 more
  1. 20223D-LDM: Neural Implicit 3D Shape Generation with Latent Diffusion Modelscited by 67
  2. 2024Advances in 3D Generation: A Surveycited by 62
  3. 2022Fast Point Cloud Generation with Straight Flowscited by 56
  4. 2023Instruct 3D-to-3D: Text Instruction Guided 3D-to-3D conversioncited by 47
  5. 2021Category-Level Metric Scale Object Shape and Pose Estimationcited by 40
  6. 2022Density-preserving Deep Point Cloud Compressioncited by 39
  7. 2021Octree Transformer: Autoregressive 3D Shape Generation on Hierarchically Structured Sequencescited by 38
  8. 2024RodinHD: High-Fidelity 3D Avatar Generation with Diffusion Modelscited by 36
  9. 2021Neural Surface Mapscited by 34
  10. 2024TexPainter: Generative Mesh Texturing with Multi-view Consistencycited by 29
  11. 2024Controllable Text-to-3D Generation via Surface-Aligned Gaussian Splattingcited by 26
  12. 20223DAC: Learning Attribute Compression for Point Cloudscited by 22
  13. 2022Self-Supervised Representation Learning for CADcited by 22
  14. 2022ALTO: Alternating Latent Topologies for Implicit 3D Reconstructioncited by 21
  15. 2022NeuralVDB: High-resolution Sparse Volume Representation using Hierarchical Neural Networkscited by 20
  16. 2022NeuForm: Adaptive Overfitting for Neural Shape Editingcited by 18
  17. 2024Imagination Policy: Using Generative Point Cloud Models for Learning Manipulation Policiescited by 18
  18. 2025Nautilus: Locality-aware Autoencoder for Scalable Mesh Generationcited by 18
  19. 20213DIAS: 3D Shape Reconstruction with Implicit Algebraic Surfacescited by 17
  20. 20243D Mesh Editing using Masked LRMscited by 17
  21. 2021HandFoldingNet: A 3D Hand Pose Estimation Network Using Multiscale-Feature Guided Folding of a 2D Hand Skeletoncited by 16
  22. 2023Learning Object-Centric Neural Scattering Functions for Free-Viewpoint Relighting and Scene Compositioncited by 15
  23. 2024DIRECT-3D: Learning Direct Text-to-3D Generation on Massive Noisy 3D Datacited by 15
  24. 2025Eval3D: Interpretable and Fine-grained Evaluation for 3D Generationcited by 15
  25. 2021DeepMesh: Differentiable Iso-Surface Extractioncited by 14
  26. 2022TetraDiffusion: Tetrahedral Diffusion Models for 3D Shape Generationcited by 14
  27. 2024PASTA: Controllable Part-Aware Shape Generation with Autoregressive Transformerscited by 14
  28. 2021Place recognition survey: An update on deep learning approachescited by 13
  29. 2021AIR-Nets: An Attention-Based Framework for Locally Conditioned Implicit Representationscited by 13
  30. 2022Volumetric Disentanglement for 3D Scene Manipulationcited by 13
  31. 2022Laplacian2Mesh: Laplacian-Based Mesh Understandingcited by 11
  32. 2022PointMCD: Boosting Deep Point Cloud Encoders via Multi-view Cross-modal Distillation for 3D Shape Recognitioncited by 10
  33. 2023Humans as Light Bulbs: 3D Human Reconstruction from Thermal Reflectioncited by 10
  34. 2026LATO: 3D Mesh Flow Matching with Structured TOpology Preserving LAtentscited by 10
  35. 2021PolyNet: Polynomial Neural Network for 3D Shape Recognition with PolyShape Representationcited by 9
  36. 2022Neural Convolutional Surfacescited by 9
  37. 2022Remote Sensing Novel View Synthesis with Implicit Multiplane Representationscited by 9
  38. 2022What's the Situation with Intelligent Mesh Generation: A Survey and Perspectivescited by 9

50 most cited of 128 All 128 (JSON)