mlsanityData to 7 Oct 2026

Learning elementary structures for 3D shape generation and matching

arXiv 1908.04725 ↗First posted 13 Aug 2019cs.CV cs.AIcited by 98

Not on the map. Why?

Abstract (arXiv)

We propose to represent shapes as the deformation and combination of learnable elementary 3D structures, which are primitives resulting from training over a collection of shape. We demonstrate that the learned elementary 3D structures lead to clear improvements in 3D shape generation and matching. More precisely, we present two complementary approaches for learning elementary structures: (i) patch deformation learning and (ii) point translation learning. Both approaches can be extended to abstract structures of higher dimensions for improved results. We evaluate our method on two tasks: reconstructing ShapeNet objects and estimating dense correspondences between human scans (FAUST inter challenge). We show 16% improvement over surface deformation approaches for shape reconstruction and outperform FAUST inter challenge state of the art by 6%.

Key facts. Cited by 98 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: 25; 2022: 24; 2023: 23; 2024: 15; 2025: 7; 2026: 4.

98 papers.

Sort:

By area:

  1. 2021Neural Fields in Visual Computing and Beyondcited by 539
  2. 2021A-SDF: Learning Disentangled Signed Distance Functions for Articulated Shape Representationcited by 113
  3. 2023Neural Kernel Surface Reconstructioncited by 102
  4. 2021Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networkscited by 101
  5. 2021The Power of Points for Modeling Humans in Clothingcited by 90
  6. 2021SCALE: Modeling Clothed Humans with a Surface Codec of Articulated Local Elementscited by 72
  7. 2021Deep Implicit Moving Least-Squares Functions for 3D Reconstructioncited by 67
  8. 2021Neural Fields as Learnable Kernels for 3D Reconstructioncited by 58
  9. 2023Diffusion 3D Features (Diff3F): Decorating Untextured Shapes with Distilled Semantic Featurescited by 55
  10. 2022Learning Implicit Templates for Point-Based Clothed Human Modelingcited by 50
  11. 2022Towards High-Fidelity Single-view Holistic Reconstruction of Indoor Scenescited by 43
  12. 2023D2CSG: Unsupervised Learning of Compact CSG Trees with Dual Complements and Dropoutscited by 39
38 more
  1. 2022Topology-Preserving Shape Reconstruction and Registration via Neural Diffeomorphic Flowcited by 38
  2. 2022Learned Vertex Descent: A New Direction for 3D Human Model Fittingcited by 37
  3. 2023Differentiable Blocks World: Qualitative 3D Decomposition by Rendering Primitivescited by 37
  4. 2023PartNeRF: Generating Part-Aware Editable 3D Shapes without 3D Supervisioncited by 36
  5. 2021Neural Surface Mapscited by 34
  6. 2024An Object is Worth 64x64 Pixels: Generating 3D Object via Image Diffusioncited by 34
  7. 2022ConDor: Self-Supervised Canonicalization of 3D Pose for Partial Shapescited by 31
  8. 2021Multiway Non-rigid Point Cloud Registration via Learned Functional Map Synchronizationcited by 30
  9. 2022SCOOP: Self-Supervised Correspondence and Optimization-Based Scene Flowcited by 28
  10. 2021OctField: Hierarchical Implicit Functions for 3D Modelingcited by 25
  11. 2022Few 'Zero Level Set'-Shot Learning of Shape Signed Distance Functions in Feature Spacecited by 22
  12. 2021Learning 3D Dense Correspondence via Canonical Point Autoencodercited by 21
  13. 2023CloSET: Modeling Clothed Humans on Continuous Surface with Explicit Template Decompositioncited by 21
  14. 2023NICP: Neural ICP for 3D Human Registration at Scalecited by 21
  15. 2022Flattening-Net: Deep Regular 2D Representation for 3D Point Cloud Analysiscited by 19
  16. 2023SE-ORNet: Self-Ensembling Orientation-aware Network for Unsupervised Point Cloud Shape Correspondencecited by 19
  17. 2022NeuForm: Adaptive Overfitting for Neural Shape Editingcited by 18
  18. 2022Shape-Pose Disentanglement using SE(3)-equivariant Vector Neuronscited by 16
  19. 2023Neural Vector Fields: Implicit Representation by Explicit Learningcited by 16
  20. 2024Unsupervised Occupancy Learning from Sparse Point Cloudcited by 15
  21. 2024Flatten Anything: Unsupervised Neural Surface Parameterizationcited by 15
  22. 2024Atlas Gaussians Diffusion for 3D Generationcited by 15
  23. 2023Point2SSM: Learning Morphological Variations of Anatomies from Point Cloudcited by 14
  24. 2024PASTA: Controllable Part-Aware Shape Generation with Autoregressive Transformerscited by 14
  25. 2021Discovering 3D Parts from Image Collectionscited by 13
  26. 2022Implicit field supervision for robust non-rigid shape matchingcited by 13
  27. 2023Mixing-Denoising Generalizable Occupancy Networkscited by 12
  28. 2024SRIF: Semantic Shape Registration Empowered by Diffusion-based Image Morphing and Flow Estimationcited by 12
  29. 2022MonteBoxFinder: Detecting and Filtering Primitives to Fit a Noisy Point Cloudcited by 11
  30. 2023CCuantuMM: Cycle-Consistent Quantum-Hybrid Matching of Multiple Shapescited by 11
  31. 2023A Survey and Benchmark of Automatic Surface Reconstruction from Point Cloudscited by 10
  32. 2023Robustifying Generalizable Implicit Shape Networks with a Tunable Non-Parametric Modelcited by 10
  33. 2024DV-Matcher: Deformation-based Non-Rigid Point Cloud Matching Guided by Pre-trained Visual Featurescited by 10
  34. 2022Test-time Adaptation with Slot-Centric Modelscited by 9
  35. 2022Neural Convolutional Surfacescited by 9
  36. 2023SCoDA: Domain Adaptive Shape Completion for Real Scanscited by 9
  37. 2022Reduced Representation of Deformation Fields for Effective Non-rigid Shape Matchingcited by 8
  38. 2021Temporally-Coherent Surface Reconstruction via Metric-Consistent Atlasescited by 7

50 most cited of 98 All 98 (JSON)