mlsanityData to 14 Oct 2026

Deformable Shape Completion with Graph Convolutional Autoencoders

arXiv 1712.00268 ↗First posted 1 Dec 2017cs.CVcited by 50

Not on the map. Why?

Abstract (arXiv)

The availability of affordable and portable depth sensors has made scanning objects and people simpler than ever. However, dealing with occlusions and missing parts is still a significant challenge. The problem of reconstructing a (possibly non-rigidly moving) 3D object from a single or multiple partial scans has received increasing attention in recent years. In this work, we propose a novel learning-based method for the completion of partial shapes. Unlike the majority of existing approaches, our method focuses on objects that can undergo non-rigid deformations. The core of our method is a variational autoencoder with graph convolutional operations that learns a latent space for complete realistic shapes. At inference, we optimize to find the representation in this latent space that best fits the generated shape to the known partial input. The completed shape exhibits a realistic appearance on the unknown part. We show promising results towards the completion of synthetic and real scans of human body and face meshes exhibiting different styles of articulation and partiality.

Key facts. Cited by 50 papers in the map (data through 14 Oct 2026). First posted on arXiv 1 Dec 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 12; 2022: 13; 2023: 11; 2024: 8; 2025: 4; 2026: 2.

50 papers.

Sort:

By area:

  1. 2022LION: Latent Point Diffusion Models for 3D Shape Generationcited by 553
  2. 2022ShapeFormer: Transformer-based Shape Completion via Sparse Representationcited by 106
  3. 2023Neural Kernel Surface Reconstructioncited by 104
  4. 2021Neural Fields as Learnable Kernels for 3D Reconstructioncited by 58
  5. 2024RangeLDM: Fast Realistic LiDAR Point Cloud Generationcited by 47
  6. 2021ARAPReg: An As-Rigid-As Possible Regularization Loss for Learning Deformable Shape Generatorscited by 40
  7. 2021Normalized Avatar Synthesis Using StyleGAN and Perceptual Refinementcited by 36
  8. 2021ASFM-Net: Asymmetrical Siamese Feature Matching Network for Point Completioncited by 28
  9. 2022Neural Jacobian Fields: Learning Intrinsic Mappings of Arbitrary Meshescited by 28
  10. 2024SpaceMesh: A Continuous Representation for Learning Manifold Surface Meshescited by 20
  11. 2021Deep Graph Convolutional Networks for Wind Speed Predictioncited by 19
  12. 2021Sparse to Dense Dynamic 3D Facial Expression Generationcited by 19
38 more
  1. 2021Frame Averaging for Equivariant Shape Space Learningcited by 19
  2. 20213D Shape Variational Autoencoder Latent Disentanglement via Mini-Batch Feature Swapping for Bodies and Facescited by 15
  3. 2023Doodle Your 3D: From Abstract Freehand Sketches to Precise 3D Shapescited by 14
  4. 2021Learning Feature Aggregation for Deep 3D Morphable Modelscited by 13
  5. 2022Deep Structural Causal Shape Modelscited by 11
  6. 2023GenCorres: Consistent Shape Matching via Coupled Implicit-Explicit Shape Generative Modelscited by 11
  7. 2023SCoDA: Domain Adaptive Shape Completion for Real Scanscited by 9
  8. 2022Generating Multiple 4D Expression Transitions by Learning Face Landmark Trajectoriescited by 7
  9. 2024Shape Non-rigid Kinematics (SNK): A Zero-Shot Method for Non-Rigid Shape Matching via Unsupervised Functional Map Regularized Reconstructioncited by 7
  10. 2025U4D: Uncertainty-Aware 4D World Modeling from LiDAR Sequencescited by 7
  11. 2022Structure-Aware NeRF without Posed Camera via Epipolar Constraintcited by 6
  12. 20233D Generative Model Latent Disentanglement via Local Eigenprojectioncited by 6
  13. 2025OT-Talk: Animating 3D Talking Head with Optimal Transportationcited by 6
  14. 2022A Generative Shape Compositional Framework to Synthesise Populations of Virtual Chimaerascited by 5
  15. 2023LASA: Instance Reconstruction from Real Scans using A Large-scale Aligned Shape Annotation Datasetcited by 5
  16. 2021Learning Spectral Unions of Partial Deformable 3D Shapescited by 4
  17. 2021Dense Graph Convolutional Neural Networks on 3D Meshes for 3D Object Segmentation and Classificationcited by 4
  18. 2023Adaptive Local Basis Functions for Shape Completioncited by 4
  19. 2022Surface Analysis with Vision Transformerscited by 3
  20. 2022Transfer Learning using Spectral Convolutional Autoencoders on Semi-Regular Surface Meshescited by 3
  21. 2025GenAnalysis: Joint Shape Analysis by Learning Man-Made Shape Generators with Deformation Regularizationscited by 3
  22. 2021A 3D Mesh-based Lifting-and-Projection Network for Human Pose Transfercited by 2
  23. 2024Self-Supervised Dual Contouringcited by 2
  24. 2022GCN-FFNN: A Two-Stream Deep Model for Learning Solution to Partial Differential Equationscited by 1
  25. 2022Deep Active Latent Surfaces for Medical Geometriescited by 1
  26. 2023Stability and Generalization of Hypergraph Collaborative Networkscited by 1
  27. 2023WrappingNet: Mesh Autoencoder via Deep Sphere Deformationcited by 1
  28. 2023Unsupervised Representation Learning for Diverse Deformable Shape Collectionscited by 1
  29. 2024CADGL: Context-Aware Deep Graph Learning for Predicting Drug-Drug Interactionscited by 1
  30. 2024Disentangling Hippocampal Shape Variations: A Study of Neurological Disorders Using Mesh Variational Autoencoder with Contrastive Learningcited by 1
  31. 2024FaceCom: Towards High-fidelity 3D Facial Shape Completion via Optimization and Inpainting Guidancecited by 1
  32. 2025TopoDiT-3D: Topology-Aware Diffusion Transformer with Bottleneck Structure for 3D Point Cloud Generationcited by 1
  33. 2022Implicit Shape Completion via Adversarial Shape Priorscited by 0
  34. 2022Pixel-Aligned Non-parametric Hand Mesh Reconstructioncited by 0
  35. 2023Towards AI-Architecture Liberty: A Comprehensive Survey on Design and Generation of Virtual Architecture by Deep Learningcited by 0
  36. 2024LISR: Learning Linear 3D Implicit Surface Representation Using Compactly Supported Radial Basis Functionscited by 0
  37. 2026A 3D mesh convolution-based autoencoder for geometry compressioncited by 0
  38. 2026A Strong Linear Baseline for Whole-Heart Cardiac Shape Completion on CT, with an Open Eleven-Structure Statistical Shape Modelcited by 0