mlsanityData to 14 Oct 2026

Intuitive Shape Editing in Latent Space

arXiv 2111.12488 ↗First posted 24 Nov 2021cs.CV cs.GR cs.LGcited by 7

Not on the map. Why?

Abstract (arXiv)

The use of autoencoders for shape editing or generation through latent space manipulation suffers from unpredictable changes in the output shape. Our autoencoder-based method enables intuitive shape editing in latent space by disentangling latent sub-spaces into style variables and control points on the surface that can be manipulated independently. The key idea is adding a Lipschitz-type constraint to the loss function, i.e. bounding the change of the output shape proportionally to the change in latent space, leading to interpretable latent space representations. The control points on the surface that are part of the latent code of an object can then be freely moved, allowing for intuitive shape editing directly in latent space. We evaluate our method by comparing to state-of-the-art data-driven shape editing methods. We further demonstrate the expressiveness of our learned latent space by leveraging it for unsupervised part segmentation.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 39 of its 59 references that are in the map. First posted on arXiv 24 Nov 2021.

Builds on

39 of 59 references.

References · 39

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  3. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  4. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  5. 2013Auto-Encoding Variational Bayescited by 4,053
  6. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
  7. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  8. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  9. 2014Conditional Generative Adversarial Netscited by 2,162
  10. 2017Decoupled Weight Decay Regularizationcited by 1,831
  11. 2019Generating Diverse High-Fidelity Images with VQ-VAE-2cited by 1,387
  12. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 979
27 more
  1. 2016InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Netscited by 860
  2. 2019On the Convergence of Adam and Beyondcited by 841
  3. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  4. 2018Pixel2Mesh: Generating 3D Mesh Models from Single RGB Imagescited by 651
  5. 2020StyleFlow: Attribute-conditioned Exploration of StyleGAN-Generated Images using Conditional Continuous Normalizing Flowscited by 349
  6. 2019SDM-NET: Deep Generative Network for Structured Deformable Meshcited by 113
  7. 2019Neural Cages for Detail-Preserving 3D Deformationscited by 106
  8. 2018MeshNet: Mesh Neural Network for 3D Shape Representationcited by 95
  9. 2019BAE-NET: Branched Autoencoder for Shape Co-Segmentationcited by 89
  10. 2017Variational Autoencoders for Deforming 3D Mesh Modelscited by 70
  11. 2020Unsupervised Shape and Pose Disentanglement for 3D Meshescited by 61
  12. 20193DN: 3D Deformation Networkcited by 60
  13. 2019StructureNet: Hierarchical Graph Networks for 3D Shape Generationcited by 59
  14. 2020LIMP: Learning Latent Shape Representations with Metric Preservation Priorscited by 55
  15. 2020DECOR-GAN: 3D Shape Detailization by Conditional Refinementcited by 45
  16. 2021Joint Learning of 3D Shape Retrieval and Deformationcited by 42
  17. 2018Geometric Understanding of Deep Learningcited by 41
  18. 2021DeepMetaHandles: Learning Deformation Meta-Handles of 3D Meshes with Biharmonic Coordinatescited by 37
  19. 2019Geometric Disentanglement for Generative Latent Shape Modelscited by 30
  20. 2020Learning Generative Models of Shape Handlescited by 25
  21. 2019Unsupervised cycle-consistent deformation for shape matchingcited by 23
  22. 2021SP-GAN: Sphere-Guided 3D Shape Generation and Manipulationcited by 21
  23. 2021Learning disentangled representations via product manifold projectioncited by 20
  24. 2018Reversible Harmonic Maps between Discrete Surfacescited by 19
  25. 2021Augmenting Implicit Neural Shape Representations with Explicit Deformation Fieldscited by 19
  26. 2018ALIGNet: Partial-Shape Agnostic Alignment via Unsupervised Learningcited by 11
  27. 2020DeformSyncNet: Deformation Transfer via Synchronized Shape Deformation Spacescited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 3; 2023: 2; 2024: 0; 2025: 1; 2026: 1.

7 papers.

  1. 2022Learning Smooth Neural Functions via Lipschitz Regularizationcited by 86
  2. 2023PartNeRF: Generating Part-Aware Editable 3D Shapes without 3D Supervisioncited by 36
  3. 2022Text and Image Guided 3D Avatar Generation and Manipulationcited by 35
  4. 2022Spelunking the Deep: Guaranteed Queries on General Neural Implicit Surfaces via Range Analysiscited by 11
  5. 2023Neural Implicit Shape Editing using Boundary Sensitivitycited by 4
  6. 2025Regularized interpolation in 4D neural fields enables optimization of 3D printed geometriescited by 1
  7. 2026GENIE: Gram-Eigenmode INR Editing with Closed-Form Geometry Updatescited by 0