mlsanityData to 14 Oct 2026

Neural Cages for Detail-Preserving 3D Deformations

arXiv 1912.06395 ↗First posted 13 Dec 2019cs.GR cs.CV cs.LGcited by 106

Not on the map. Why?

Abstract (arXiv)

We propose a novel learnable representation for detail-preserving shape deformation. The goal of our method is to warp a source shape to match the general structure of a target shape, while preserving the surface details of the source. Our method extends a traditional cage-based deformation technique, where the source shape is enclosed by a coarse control mesh termed cage, and translations prescribed on the cage vertices are interpolated to any point on the source mesh via special weight functions. The use of this sparse cage scaffolding enables preserving surface details regardless of the shape's intricacy and topology. Our key contribution is a novel neural network architecture for predicting deformations by controlling the cage. We incorporate a differentiable cage-based deformation module in our architecture, and train our network end-to-end. Our method can be trained with common collections of 3D models in an unsupervised fashion, without any cage-specific annotations. We demonstrate the utility of our method for synthesizing shape variations and deformation transfer.

Key facts. Cited by 106 papers in the map (data through 14 Oct 2026). First posted on arXiv 13 Dec 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 15; 2022: 21; 2023: 24; 2024: 18; 2025: 14; 2026: 14.

106 papers.

Sort:

By area:

  1. 2021Advances in Neural Renderingcited by 365
  2. 2023SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenescited by 347
  3. 2022NeRF-Editing: Geometry Editing of Neural Radiance Fieldscited by 217
  4. 2021FS-Net: Fast Shape-based Network for Category-Level 6D Object Pose Estimation with Decoupled Rotation Mechanismcited by 121
  5. 2023Drivable 3D Gaussian Avatarscited by 120
  6. 2022MagicPony: Learning Articulated 3D Animals in the Wildcited by 112
  7. 2022Generative Neural Articulated Radiance Fieldscited by 101
  8. 2023TextDeformer: Geometry Manipulation using Text Guidancecited by 94
  9. 2022TANGO: Text-driven Photorealistic and Robust 3D Stylization via Lighting Decompositioncited by 83
  10. 2022Deforming Radiance Fields with Cagescited by 78
  11. 2024Advances in 3D Generation: A Surveycited by 63
  12. 2021Geometry-Consistent Neural Shape Representation with Implicit Displacement Fieldscited by 60
38 more
  1. 20213DStyleNet: Creating 3D Shapes with Geometric and Texture Style Variationscited by 58
  2. 2021Learning Skeletal Articulations with Neural Blend Shapescited by 53
  3. 2021KeypointDeformer: Unsupervised 3D Keypoint Discovery for Shape Controlcited by 51
  4. 2021Joint Learning of 3D Shape Retrieval and Deformationcited by 42
  5. 2023Controllable Mesh Generation Through Sparse Latent Point Diffusion Modelscited by 41
  6. 2023NeuralEditor: Editing Neural Radiance Fields via Manipulating Point Cloudscited by 41
  7. 2021ARAPReg: An As-Rigid-As Possible Regularization Loss for Learning Deformable Shape Generatorscited by 40
  8. 2021DeepMetaHandles: Learning Deformation Meta-Handles of 3D Meshes with Biharmonic Coordinatescited by 37
  9. 2022VolTeMorph: Realtime, Controllable and Generalisable Animation of Volumetric Representationscited by 36
  10. 2023PartNeRF: Generating Part-Aware Editable 3D Shapes without 3D Supervisioncited by 36
  11. 2024Tailor3D: Customized 3D Assets Editing and Generation with Dual-Side Imagescited by 35
  12. 2022Neural Template: Topology-aware Reconstruction and Disentangled Generation of 3D Meshescited by 34
  13. 20213D Pose Transfer with Correspondence Learning and Mesh Refinementcited by 30
  14. 2022SPAGHETTI: Editing Implicit Shapes Through Part Aware Generationcited by 28
  15. 2022Neural Jacobian Fields: Learning Intrinsic Mappings of Arbitrary Meshescited by 28
  16. 2024Mesh-based Gaussian Splatting for Real-time Large-scale Deformationcited by 28
  17. 2023CADSim: Robust and Scalable in-the-wild 3D Reconstruction for Controllable Sensor Simulationcited by 26
  18. 2024Garment3DGen: 3D Garment Stylization and Texture Generationcited by 26
  19. 2023As-Plausible-As-Possible: Plausibility-Aware Mesh Deformation Using 2D Diffusion Priorscited by 25
  20. 2022Learning Whole Heart Mesh Generation From Patient Images For Computational Simulationscited by 21
  21. 2022Unsupervised 3D Pose Transfer with Cross Consistency and Dual Reconstructioncited by 21
  22. 2022SPARC: Sparse Render-and-Compare for CAD model alignment in a single RGB imagecited by 19
  23. 2023NCP: Neural Correspondence Prior for Effective Unsupervised Shape Matchingcited by 18
  24. 2022SPIDR: SDF-based Neural Point Fields for Illumination and Deformationcited by 17
  25. 2024MeshUp: Multi-Target Mesh Deformation via Blended Score Distillationcited by 17
  26. 2021GLASS: Geometric Latent Augmentation for Shape Spacescited by 16
  27. 2023TapMo: Shape-aware Motion Generation of Skeleton-free Characterscited by 16
  28. 2024CT4D: Consistent Text-to-4D Generation with Animatable Meshescited by 14
  29. 2025Geometry in Style: 3D Stylization via Surface Normal Deformationcited by 14
  30. 20254D-LRM: Large Space-Time Reconstruction Model From and To Any View at Any Timecited by 14
  31. 2023Zero-shot Pose Transfer for Unrigged Stylized 3D Characterscited by 13
  32. 2025Edit360: 2D Image Edits to 3D Assets from Any Anglecited by 13
  33. 2023Weakly-supervised 3D Pose Transfer with Keypointscited by 12
  34. 2023U-RED: Unsupervised 3D Shape Retrieval and Deformation for Partial Point Cloudscited by 12
  35. 2022Towards Self-Supervised Category-Level Object Pose and Size Estimationcited by 11
  36. 2024HeadEvolver: Text to Head Avatars via Expressive and Attribute-Preserving Mesh Deformationcited by 11
  37. 2022Neural Vector Fields for Implicit Surface Representation and Inferencecited by 10
  38. 2023DPF-Net: Combining Explicit Shape Priors in Deformable Primitive Field for Unsupervised Structural Reconstruction of 3D Objectscited by 10

50 most cited of 106 All 106 (JSON)