mlsanityData to 7 Oct 2026

SDM-NET: Deep Generative Network for Structured Deformable Mesh

arXiv 1908.04520 ↗First posted 13 Aug 2019cs.GR cs.CVcited by 113

Not on the map. Why?

Abstract (arXiv)

We introduce SDM-NET, a deep generative neural network which produces structured deformable meshes. Specifically, the network is trained to generate a spatial arrangement of closed, deformable mesh parts, which respect the global part structure of a shape collection, e.g., chairs, airplanes, etc. Our key observation is that while the overall structure of a 3D shape can be complex, the shape can usually be decomposed into a set of parts, each homeomorphic to a box, and the finer-scale geometry of the part can be recovered by deforming the box. The architecture of SDM-NET is that of a two-level variational autoencoder (VAE). At the part level, a PartVAE learns a deformable model of part geometries. At the structural level, we train a Structured Parts VAE (SP-VAE), which jointly learns the part structure of a shape collection and the part geometries, ensuring a coherence between global shape structure and surface details. Through extensive experiments and comparisons with the state-of-the-art deep generative models of shapes, we demonstrate the superiority of SDM-NET in generating meshes with visual quality, flexible topology, and meaningful structures, which benefit shape interpolation and other subsequently modeling tasks.

Key facts. Cited by 113 papers in the map (data through 7 Oct 2026). First posted on arXiv 13 Aug 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 26; 2022: 17; 2023: 26; 2024: 20; 2025: 17; 2026: 7.

113 papers.

Sort:

By area:

  1. 2022LION: Latent Point Diffusion Models for 3D Shape Generationcited by 552
  2. 2022Latent-NeRF for Shape-Guided Generation of 3D Shapes and Texturescited by 506
  3. 2021Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesiscited by 459
  4. 2023XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchiescited by 183
  5. 2022Dream3D: Zero-Shot Text-to-3D Synthesis Using 3D Shape Prior and Text-to-Image Diffusion Modelscited by 151
  6. 2023Let 2D Diffusion Model Know 3D-Consistency for Robust Text-to-3D Generationcited by 133
  7. 2024Recent Advances in 3D Gaussian Splattingcited by 130
  8. 2021Deep Generative Models in Engineering Design: A Reviewcited by 103
  9. 2021Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networkscited by 101
  10. 2021Holistic 3D Scene Understanding from a Single Image with Implicit Representationcited by 94
  11. 2021JoinABLe: Learning Bottom-up Assembly of Parametric CAD Jointscited by 77
  12. 2021You Only Hypothesize Once: Point Cloud Registration with Rotation-equivariant Descriptorscited by 68
38 more
  1. 2022Towards Implicit Text-Guided 3D Shape Generationcited by 68
  2. 2024SINGAPO: Single Image Controlled Generation of Articulated Parts in Objectscited by 66
  3. 2021CAPRI-Net: Learning Compact CAD Shapes with Adaptive Primitive Assemblycited by 62
  4. 2024Advances in 3D Generation: A Surveycited by 62
  5. 2024Part123: Part-aware 3D Reconstruction from a Single-view Imagecited by 54
  6. 2021Neural Marching Cubescited by 50
  7. 2023CAGE: Controllable Articulation GEnerationcited by 50
  8. 2024RangeLDM: Fast Realistic LiDAR Point Cloud Generationcited by 45
  9. 2021Unsupervised Learning for Cuboid Shape Abstraction via Joint Segmentation from Point Cloudscited by 44
  10. 2024PhyRecon: Physically Plausible Neural Scene Reconstructioncited by 44
  11. 2021Joint Learning of 3D Shape Retrieval and Deformationcited by 41
  12. 2025Articulate AnyMesh: Open-Vocabulary 3D Articulated Objects Modelingcited by 41
  13. 2021ARAPReg: An As-Rigid-As Possible Regularization Loss for Learning Deformable Shape Generatorscited by 40
  14. 2024MeshArt: Generating Articulated Meshes with Structure-Guided Transformerscited by 40
  15. 2022AUV-Net: Learning Aligned UV Maps for Texture Transfer and Synthesiscited by 39
  16. 2023SceneHGN: Hierarchical Graph Networks for 3D Indoor Scene Generation with Fine-Grained Geometrycited by 38
  17. 2021DeepMetaHandles: Learning Deformation Meta-Handles of 3D Meshes with Biharmonic Coordinatescited by 36
  18. 2023PartNeRF: Generating Part-Aware Editable 3D Shapes without 3D Supervisioncited by 36
  19. 2021RGL-NET: A Recurrent Graph Learning framework for Progressive Part Assemblycited by 35
  20. 2021PTR: A Benchmark for Part-based Conceptual, Relational, and Physical Reasoningcited by 34
  21. 2022Neural Template: Topology-aware Reconstruction and Disentangled Generation of 3D Meshescited by 34
  22. 2024An Object is Worth 64x64 Pixels: Generating 3D Object via Image Diffusioncited by 34
  23. 2023DiffFacto: Controllable Part-Based 3D Point Cloud Generation with Cross Diffusioncited by 32
  24. 2022SPAGHETTI: Editing Implicit Shapes Through Part Aware Generationcited by 28
  25. 2022Neural Jacobian Fields: Learning Intrinsic Mappings of Arbitrary Meshescited by 28
  26. 2024Mesh-based Gaussian Splatting for Real-time Large-scale Deformationcited by 28
  27. 2021BIKED: A Dataset for Computational Bicycle Design with Machine Learning Benchmarkscited by 27
  28. 2024Controllable Text-to-3D Generation via Surface-Aligned Gaussian Splattingcited by 26
  29. 2025From One to More: Contextual Part Latents for 3D Generationcited by 26
  30. 2021OctField: Hierarchical Implicit Functions for 3D Modelingcited by 25
  31. 2023NAP: Neural 3D Articulation Priorcited by 25
  32. 2023AI-Generated Content (AIGC) for Various Data Modalities: A Surveycited by 25
  33. 2023Text-to-3D Generation with Bidirectional Diffusion using both 2D and 3D priorscited by 24
  34. 2023Category-Level Multi-Part Multi-Joint 3D Shape Assemblycited by 22
  35. 2023CAD: Photorealistic 3D Generation via Adversarial Distillationcited by 18
  36. 20223D Part Assembly Generation with Instance Encoded Transformercited by 17
  37. 2024Generative 3D Part Assembly via Part-Whole-Hierarchy Message Passingcited by 17
  38. 2021GLASS: Geometric Latent Augmentation for Shape Spacescited by 16

50 most cited of 113 All 113 (JSON)