Learning Canonical Embedding for Non-rigid Shape Matching
Not on the map. Why?
Abstract (arXiv)
This paper provides a novel framework that learns canonical embeddings for non-rigid shape matching. In contrast to prior work in this direction, our framework is trained end-to-end and thus avoids instabilities and constraints associated with the commonly-used Laplace-Beltrami basis or sequential optimization schemes. On multiple datasets, we demonstrate that learning self symmetry maps with a deep functional map projects 3D shapes into a low dimensional canonical embedding that facilitates non-rigid shape correspondence via a simple nearest neighbor search. Our framework outperforms multiple recent learning based methods on FAUST and SHREC benchmarks while being computationally cheaper, data-efficient, and robust.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 25 of its 46 references that are in the map. First posted on arXiv 6 Oct 2021.
Builds on
25 of 46 references.
References · 25
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
- 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
- 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,591
- 2016Geometric deep learning on graphs and manifolds using mixture model CNNscited by 468
- 2017Learning from Synthetic Humanscited by 359
- 20183D-CODED : 3D Correspondences by Deep Deformationcited by 160
- 2017Deep Functional Maps: Structured Prediction for Dense Shape Correspondencecited by 134
- 2020Deep Geometric Functional Maps: Robust Feature Learning for Shape Correspondencecited by 125
- 2016Learning shape correspondence with anisotropic convolutional neural networkscited by 95
- 2018Unsupervised Deep Learning for Structured Shape Matchingcited by 81
- 2020Continuous Surface Embeddingscited by 80
- 2018Continuous and Orientation-preserving Correspondences via Functional Mapscited by 77
13 more
- 2019Smooth Shells: Multi-Scale Shape Registration with Functional Mapscited by 72
- 2015Partial Functional Correspondencecited by 61
- 2016VConv-DAE: Deep Volumetric Shape Learning Without Object Labelscited by 50
- 2020Correspondence Learning via Linearly-invariant Embeddingcited by 48
- 2019Cyclic Functional Mapping: Self-supervised correspondence between non-isometric deformable shapescited by 30
- 2015Dense Human Body Correspondences Using Convolutional Networkscited by 26
- 2020Unsupervised Learning of Category-Specific Symmetric 3D Keypoints from Point Setscited by 23
- 2019A Functional Representation for Graph Matchingcited by 13
- 2020MapTree: Recovering Multiple Solutions in the Space of Mapscited by 11
- 2020Wavelet-based Heat Kernel Derivatives: Towards Informative Localized Shape Analysiscited by 8
- 2020Weakly Supervised Deep Functional Map for Shape Matchingcited by 8
- 2020SymmetryNet: Learning to Predict Reflectional and Rotational Symmetries of 3D Shapes from Single-View RGB-D Imagescited by 6
- 2021Matrix Decomposition on Graphs: A Functional Viewcited by 2
Built on by
Citing papers per year: 2022: 1.
1 paper.