mlsanityData to 7 Oct 2026

Learning Shape Abstractions by Assembling Volumetric Primitives

arXiv 1612.00404 ↗First posted 1 Dec 2016cs.CVcited by 181

Not on the map. Why?

Abstract (arXiv)

We present a learning framework for abstracting complex shapes by learning to assemble objects using 3D volumetric primitives. In addition to generating simple and geometrically interpretable explanations of 3D objects, our framework also allows us to automatically discover and exploit consistent structure in the data. We demonstrate that using our method allows predicting shape representations which can be leveraged for obtaining a consistent parsing across the instances of a shape collection and constructing an interpretable shape similarity measure. We also examine applications for image-based prediction as well as shape manipulation.

Key facts. Cited by 181 papers in the map (data through 7 Oct 2026). First posted on arXiv 1 Dec 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 46; 2022: 37; 2023: 37; 2024: 21; 2025: 20; 2026: 20.

181 papers.

Sort:

By area:

  1. 2021Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesiscited by 459
  2. 2023LucidDreamer: Domain-free Generation of 3D Gaussian Splatting Scenescited by 228
  3. 2021ATISS: Autoregressive Transformers for Indoor Scene Synthesiscited by 195
  4. 2023Flexible Isosurface Extraction for Gradient-Based Mesh Optimizationcited by 138
  5. 2021Im2Vec: Synthesizing Vector Graphics without Vector Supervisioncited by 114
  6. 2021A-SDF: Learning Disentangled Signed Distance Functions for Articulated Shape Representationcited by 113
  7. 2021Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networkscited by 101
  8. 2022Semantic Abstraction: Open-World 3D Scene Understanding from 2D Vision-Language Modelscited by 95
  9. 2024SceneScript: Reconstructing Scenes With An Autoregressive Structured Language Modelcited by 95
  10. 2022What's in your hands? 3D Reconstruction of Generic Objects in Handscited by 90
  11. 2021Deep Implicit Moving Least-Squares Functions for 3D Reconstructioncited by 67
  12. 2023SALAD: Part-Level Latent Diffusion for 3D Shape Generation and Manipulationcited by 66
38 more
  1. 2022LASSIE: Learning Articulated Shapes from Sparse Image Ensemble via 3D Part Discoverycited by 65
  2. 2022High-fidelity 3D GAN Inversion by Pseudo-multi-view Optimizationcited by 65
  3. 2024Real2Code: Reconstruct Articulated Objects via Code Generationcited by 64
  4. 2021CAPRI-Net: Learning Compact CAD Shapes with Adaptive Primitive Assemblycited by 62
  5. 2022Approximate Convex Decomposition for 3D Meshes with Collision-Aware Concavity and Tree Searchcited by 61
  6. 2022Control-NeRF: Editable Feature Volumes for Scene Rendering and Manipulationcited by 57
  7. 2024Part123: Part-aware 3D Reconstruction from a Single-view Imagecited by 54
  8. 2021CSG-Stump: A Learning Friendly CSG-Like Representation for Interpretable Shape Parsingcited by 51
  9. 2021KeypointDeformer: Unsupervised 3D Keypoint Discovery for Shape Controlcited by 50
  10. 20243D Convex Splatting: Radiance Field Rendering with 3D Smooth Convexescited by 50
  11. 2023SECAD-Net: Self-Supervised CAD Reconstruction by Learning Sketch-Extrude Operationscited by 46
  12. 2021Unsupervised Learning for Cuboid Shape Abstraction via Joint Segmentation from Point Cloudscited by 44
  13. 2022Towards High-Fidelity Single-view Holistic Reconstruction of Indoor Scenescited by 43
  14. 2022Neural Shape Mating: Self-Supervised Object Assembly with Adversarial Shape Priorscited by 42
  15. 2021ARAPReg: An As-Rigid-As Possible Regularization Loss for Learning Deformable Shape Generatorscited by 40
  16. 2023D2CSG: Unsupervised Learning of Compact CSG Trees with Dual Complements and Dropoutscited by 39
  17. 2022ExtrudeNet: Unsupervised Inverse Sketch-and-Extrude for Shape Parsingcited by 38
  18. 2023Differentiable Blocks World: Qualitative 3D Decomposition by Rendering Primitivescited by 37
  19. 2023PartNeRF: Generating Part-Aware Editable 3D Shapes without 3D Supervisioncited by 36
  20. 2021HPNet: Deep Primitive Segmentation Using Hybrid Representationscited by 35
  21. 2022PartAfford: Part-level Affordance Discovery from 3D Objectscited by 35
  22. 2022Point Primitive Transformer for Long-Term 4D Point Cloud Video Understandingcited by 35
  23. 2023Make Encoder Great Again in 3D GAN Inversion through Geometry and Occlusion-Aware Encodingcited by 35
  24. 2022Neural Template: Topology-aware Reconstruction and Disentangled Generation of 3D Meshescited by 34
  25. 2024Img2CAD: Reverse Engineering 3D CAD Models from Images through VLM-Assisted Conditional Factorizationcited by 34
  26. 2021PC2WF: 3D Wireframe Reconstruction from Raw Point Cloudscited by 33
  27. 2022VAEL: Bridging Variational Autoencoders and Probabilistic Logic Programmingcited by 31
  28. 2021Continual Neural Mapping: Learning An Implicit Scene Representation from Sequential Observationscited by 30
  29. 2021PartGlot: Learning Shape Part Segmentation from Language Reference Gamescited by 30
  30. 2022Hi-LASSIE: High-Fidelity Articulated Shape and Skeleton Discovery from Sparse Image Ensemblecited by 30
  31. 2021Scene Synthesis via Uncertainty-Driven Attribute Synchronizationcited by 29
  32. 2021Robust and Accurate Superquadric Recovery: a Probabilistic Approachcited by 29
  33. 2022SPAGHETTI: Editing Implicit Shapes Through Part Aware Generationcited by 28
  34. 2021Unsupervised Learning of Fine Structure Generation for 3D Point Clouds by 2D Projection Matchingcited by 26
  35. 2023Self-Supervised Category-Level Articulated Object Pose Estimation with Part-Level SE(3) Equivariancecited by 26
  36. 2023GINA-3D: Learning to Generate Implicit Neural Assets in the Wildcited by 25
  37. 2021CPFN: Cascaded Primitive Fitting Networks for High-Resolution Point Cloudscited by 24
  38. 2024SceneDreamer360: Text-Driven 3D-Consistent Scene Generation with Panoramic Gaussian Splattingcited by 24

50 most cited of 181 All 181 (JSON)