pith. sign in

arxiv: 2303.10971 · v2 · submitted 2023-03-20 · 💻 cs.CV · cs.AI· cs.CG

Self-Supervised Learning for Multimodal Non-Rigid 3D Shape Matching

Dongliang Cao , Florian Bernard This is my paper

Pith reviewed 2026-05-24 09:05 UTC · model grok-4.3

classification 💻 cs.CV cs.AIcs.CG
keywords self-supervised learning3D shape matchingfunctional mapscontrastive lossmultimodalnon-rigid registrationpoint cloudsmeshes
0
0 comments X

The pith

Self-supervised learning matches non-rigid 3D shapes across meshes and point clouds by pairing functional map regularisation with contrastive coupling.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper establishes a self-supervised strategy for non-rigid 3D shape matching that works with surface meshes, complete point clouds, and partial point clouds. It combines regularisation drawn from functional maps on meshes with a contrastive loss that directly links mesh and point cloud representations during training. No labeled correspondences are required. A sympathetic reader would care because raw sensor data arrives as point clouds while meshes supply useful topology, so a method that bridges both without manual labels could improve matching quality on real-world scans and enable reuse across datasets.

Core claim

By introducing a self-supervised multimodal learning strategy that combines mesh-based functional map regularisation with a contrastive loss that couples mesh and point cloud data, the approach obtains intramodal correspondences for triangle meshes, complete point clouds, and partially observed point clouds, as well as correspondences across these data modalities, achieving state-of-the-art results on several challenging benchmark datasets even in comparison to recent supervised methods and reaching previously unseen cross-dataset generalisation ability.

What carries the argument

mesh-based functional map regularisation combined with a contrastive loss that couples mesh and point cloud data

If this is right

  • The method produces intramodal correspondences for triangle meshes, complete point clouds, and partial point clouds.
  • It also produces correspondences across mesh and point cloud modalities.
  • Performance reaches state-of-the-art levels on multiple benchmarks, including against supervised competitors.
  • Cross-dataset generalisation reaches levels not previously observed with comparable methods.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Raw point-cloud scans from sensors could be matched at mesh-level quality without first converting them to curated meshes.
  • The same coupling idea could be tested on additional modalities such as depth images or volumetric data.
  • If the contrastive term proves robust, the framework might reduce reliance on synthetic labeled datasets for training shape matchers.

Load-bearing premise

That combining mesh-based functional map regularisation with a contrastive loss coupling mesh and point cloud data will produce effective correspondences in a fully self-supervised manner without labeled data.

What would settle it

A set of standard benchmarks where the method's correspondence accuracy falls below recent supervised approaches or where cross-dataset generalisation fails to exceed prior self-supervised or supervised baselines.

Figures

Figures reproduced from arXiv: 2303.10971 by Dongliang Cao, Florian Bernard.

Figure 1
Figure 1. Figure 1: Left: Our method obtains accurate correspondences for triangle meshes, point clouds and even partially observed point clouds. Right: Proportion of correct keypoints (PCK) curves and mean geodesic errors (scores in the legend) on the SHREC’19 dataset [34] for meshes (solid lines) and point clouds (dashed lines). Existing point cloud matching methods (DPC [26], green line), or mesh-based methods applied to p… view at source ↗
Figure 2
Figure 2. Figure 2: Method overview. During training a Siamese feature extraction network with shared weights Θ learns to extract mesh features Fx, Fy for input meshes X , Y, as well as point cloud features Fˆx, Fˆy for corresponding point clouds Xˆ, Yˆ. The mesh features Fx, Fy are then used to compute bidirectional functional maps Cxy, Cyx using the parameter-free FM solver (red). In contrast, the features from point clouds… view at source ↗
Figure 3
Figure 3. Figure 3: Qualitative results of different methods applied to point clouds from the SHREC’19 dataset. Errors are indicated by red arrows. [PITH_FULL_IMAGE:figures/full_fig_p006_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Qualitative results of our method on the SHREC’19 [PITH_FULL_IMAGE:figures/full_fig_p007_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Qualitative results of different methods applied to point clouds from the HOLES subset. Errors are indicated by red arrows. [PITH_FULL_IMAGE:figures/full_fig_p008_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Qualitative results of our method on the SURREAL-PV [PITH_FULL_IMAGE:figures/full_fig_p008_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: We obtain reliable correspondences for the matching of [PITH_FULL_IMAGE:figures/full_fig_p008_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: Qualitative results on FAUST dataset with different ini [PITH_FULL_IMAGE:figures/full_fig_p011_8.png] view at source ↗
Figure 11
Figure 11. Figure 11: An example shape pair and the corresponding quali [PITH_FULL_IMAGE:figures/full_fig_p012_11.png] view at source ↗
Figure 10
Figure 10. Figure 10: Mean geodesic errors for point cloud matching in dif [PITH_FULL_IMAGE:figures/full_fig_p012_10.png] view at source ↗
Figure 12
Figure 12. Figure 12: A qualitative result from real-scanned raw point clouds [PITH_FULL_IMAGE:figures/full_fig_p013_12.png] view at source ↗
Figure 15
Figure 15. Figure 15: Qualitative results on SHREC’19 dataset of our method [PITH_FULL_IMAGE:figures/full_fig_p013_15.png] view at source ↗
Figure 13
Figure 13. Figure 13: Qualitative results on FAUST dataset of our method [PITH_FULL_IMAGE:figures/full_fig_p013_13.png] view at source ↗
Figure 17
Figure 17. Figure 17: Qualitative partial view matching results on [PITH_FULL_IMAGE:figures/full_fig_p014_17.png] view at source ↗
read the original abstract

The matching of 3D shapes has been extensively studied for shapes represented as surface meshes, as well as for shapes represented as point clouds. While point clouds are a common representation of raw real-world 3D data (e.g. from laser scanners), meshes encode rich and expressive topological information, but their creation typically requires some form of (often manual) curation. In turn, methods that purely rely on point clouds are unable to meet the matching quality of mesh-based methods that utilise the additional topological structure. In this work we close this gap by introducing a self-supervised multimodal learning strategy that combines mesh-based functional map regularisation with a contrastive loss that couples mesh and point cloud data. Our shape matching approach allows to obtain intramodal correspondences for triangle meshes, complete point clouds, and partially observed point clouds, as well as correspondences across these data modalities. We demonstrate that our method achieves state-of-the-art results on several challenging benchmark datasets even in comparison to recent supervised methods, and that our method reaches previously unseen cross-dataset generalisation ability.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

0 major / 0 minor

Summary. The manuscript introduces a self-supervised multimodal strategy for non-rigid 3D shape matching. It combines mesh-based functional map regularisation with a contrastive loss that couples mesh and point cloud data to obtain correspondences for triangle meshes, complete and partial point clouds, and across modalities. The authors claim state-of-the-art performance on challenging benchmarks, surpassing recent supervised methods, and unprecedented cross-dataset generalisation.

Significance. If the experimental claims hold, the work would be significant for bridging the quality gap between topology-rich mesh matching and raw point-cloud data from sensors via fully self-supervised training. The reported cross-dataset generalisation would be a notable advance over typical supervised approaches that often overfit to specific datasets.

Simulated Author's Rebuttal

0 responses · 2 unresolved

We thank the referee for their summary of our manuscript and for noting the potential significance of a self-supervised multimodal approach that bridges mesh-based and point-cloud matching while achieving strong cross-dataset generalization. No specific major comments were provided in the report, so we have no point-by-point responses to offer. The uncertainty in the recommendation appears to stem from the need to verify experimental claims, which we stand behind based on the full paper.

standing simulated objections not resolved
  • No specific major comments listed, preventing targeted rebuttals.
  • Only the abstract is available here, limiting our ability to address any potential detailed questions on experiments or implementation that might arise from the full manuscript.

Circularity Check

0 steps flagged

No circularity detectable

full rationale

Only the abstract is available and it contains no equations, derivations, loss formulations, or self-citations. The text describes a high-level approach (mesh-based functional map regularisation combined with contrastive loss) but supplies no technical chain that could be inspected for self-definition, fitted inputs renamed as predictions, or load-bearing self-citations. Consequently no circular step can be quoted or exhibited, and the derivation is treated as self-contained by default.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Abstract-only review provides no information on free parameters, axioms or invented entities used in the method.

pith-pipeline@v0.9.0 · 5684 in / 1082 out tokens · 40393 ms · 2026-05-24T09:05:18.711232+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

64 extracted references · 64 canonical work pages

  1. [1]

    Scape: shape completion and animation of people

    Dragomir Anguelov, Praveen Srinivasan, Daphne Koller, Se- bastian Thrun, Jim Rodgers, and James Davis. Scape: shape completion and animation of people. In ACM SIGGRAPH

    work page

  2. [2]

    Dpfm: Deep partial functional maps

    Souhaib Attaiki, Gautam Pai, and Maks Ovsjanikov. Dpfm: Deep partial functional maps. In International Conference on 3D Vision (3DV), 2021. 2, 3, 4, 7, 8

    work page 2021

  3. [3]

    The wave kernel signature: A quantum mechanical approach to shape analysis

    Mathieu Aubry, Ulrich Schlickewei, and Daniel Cremers. The wave kernel signature: A quantum mechanical approach to shape analysis. In ICCV, 2011. 2

    work page 2011

  4. [4]

    Mina: Convex mixed-integer programming for non-rigid shape alignment

    Florian Bernard, Zeeshan Khan Suri, and Christian Theobalt. Mina: Convex mixed-integer programming for non-rigid shape alignment. In CVPR, 2020. 2

    work page 2020

  5. [5]

    Faust: Dataset and evaluation for 3d mesh registration

    Federica Bogo, Javier Romero, Matthew Loper, and Michael J Black. Faust: Dataset and evaluation for 3d mesh registration. In CVPR, 2014. 5

    work page 2014

  6. [6]

    Anisotropic diffusion descriptors

    Davide Boscaini, Jonathan Masci, Emanuele Rodol `a, Michael M Bronstein, and Daniel Cremers. Anisotropic diffusion descriptors. In Computer Graphics Forum , vol- ume 35, pages 431–441. Wiley Online Library, 2016. 3

    work page 2016

  7. [7]

    Scale-invariant heat kernel signatures for non-rigid shape recognition

    Michael M Bronstein and Iasonas Kokkinos. Scale-invariant heat kernel signatures for non-rigid shape recognition. In CVPR, 2010. 2

    work page 2010

  8. [8]

    Unsupervised deep multi-shape matching

    Dongliang Cao and Florian Bernard. Unsupervised deep multi-shape matching. In ECCV, 2022. 1, 2, 3, 4, 5, 6, 7

    work page 2022

  9. [9]

    Fi- nite elements on point based surfaces

    Ulrich Clarenz, Martin Rumpf, and Alexandru C Telea. Fi- nite elements on point based surfaces. In PBG, pages 201– 211, 2004. 3

    work page 2004

  10. [10]

    Shrec’16: Partial matching of deformable shapes

    Luca Cosmo, Emanuele Rodola, Michael M Bronstein, An- drea Torsello, Daniel Cremers, and Y Sahillioglu. Shrec’16: Partial matching of deformable shapes. Proc. 3DOR , 2(9):12, 2016. 6

    work page 2016

  11. [11]

    Texture transfer during shape transformation

    Huong Quynh Dinh, Anthony Yezzi, and Greg Turk. Texture transfer during shape transformation. ACM Transactions on Graphics (ToG), 24(2):289–310, 2005. 1

    work page 2005

  12. [12]

    Deep orientation-aware functional maps: Tackling symme- try issues in shape matching

    Nicolas Donati, Etienne Corman, and Maks Ovsjanikov. Deep orientation-aware functional maps: Tackling symme- try issues in shape matching. In CVPR, 2022. 2, 4

    work page 2022

  13. [13]

    Deep geometric functional maps: Robust feature learning for shape correspondence

    Nicolas Donati, Abhishek Sharma, and Maks Ovsjanikov. Deep geometric functional maps: Robust feature learning for shape correspondence. In CVPR, 2020. 2, 5, 6, 7, 8

    work page 2020

  14. [14]

    Divergence-free shape correspondence by deformation

    Marvin Eisenberger, Zorah L ¨ahner, and Daniel Cremers. Divergence-free shape correspondence by deformation. In Computer Graphics Forum, volume 38, pages 1–12. Wiley Online Library, 2019. 2

    work page 2019

  15. [15]

    Smooth shells: Multi-scale shape registration with functional maps

    Marvin Eisenberger, Zorah Lahner, and Daniel Cremers. Smooth shells: Multi-scale shape registration with functional maps. In CVPR, 2020. 2, 6

    work page 2020

  16. [16]

    Neuromorph: Unsupervised shape interpola- tion and correspondence in one go

    Marvin Eisenberger, David Novotny, Gael Kerchenbaum, Patrick Labatut, Natalia Neverova, Daniel Cremers, and An- drea Vedaldi. Neuromorph: Unsupervised shape interpola- tion and correspondence in one go. In CVPR, 2021. 1, 4

    work page 2021

  17. [17]

    Deep shells: Unsupervised shape corre- spondence with optimal transport

    Marvin Eisenberger, Aysim Toker, Laura Leal-Taix ´e, and Daniel Cremers. Deep shells: Unsupervised shape corre- spondence with optimal transport. NIPS, 2020. 1, 2, 6

    work page 2020

  18. [18]

    Isometric multi-shape matching

    Maolin Gao, Zorah Lahner, Johan Thunberg, Daniel Cre- mers, and Florian Bernard. Isometric multi-shape matching. In CVPR, 2021. 2

    work page 2021

  19. [19]

    3d-coded: 3d cor- respondences by deep deformation

    Thibault Groueix, Matthew Fisher, Vladimir G Kim, Bryan C Russell, and Mathieu Aubry. 3d-coded: 3d cor- respondences by deep deformation. In ECCV, 2018. 1, 2, 3, 6, 8

    work page 2018

  20. [20]

    Unsupervised cycle- consistent deformation for shape matching

    Thibault Groueix, Matthew Fisher, Vladimir G Kim, Bryan C Russell, and Mathieu Aubry. Unsupervised cycle- consistent deformation for shape matching. In Computer Graphics Forum. Wiley Online Library, 2019. 1, 3

    work page 2019

  21. [21]

    Unsupervised learning of dense shape correspondence

    Oshri Halimi, Or Litany, Emanuele Rodola, Alex M Bron- stein, and Ron Kimmel. Unsupervised learning of dense shape correspondence. In CVPR, 2019. 2, 6

    work page 2019

  22. [22]

    Simulated annealing for 3d shape correspondence

    Benjamin Holzschuh, Zorah L ¨ahner, and Daniel Cremers. Simulated annealing for 3d shape correspondence. In 2020 International Conference on 3D Vision (3DV), 2020. 2

    work page 2020

  23. [23]

    Functional map networks for analyzing and exploring large shape col- lections

    Qixing Huang, Fan Wang, and Leonidas Guibas. Functional map networks for analyzing and exploring large shape col- lections. ACM Transactions on Graphics (ToG), 33(4):1–11,

    work page

  24. [24]

    Consistent zoomout: Efficient spectral map synchronization

    Ruqi Huang, Jing Ren, Peter Wonka, and Maks Ovsjanikov. Consistent zoomout: Efficient spectral map synchronization. In Computer Graphics Forum. Wiley Online Library, 2020. 2

    work page 2020

  25. [25]

    Categorical reparametrization with gumble-softmax

    Eric Jang, Shixiang Gu, and Ben Poole. Categorical reparametrization with gumble-softmax. In ICLR, 2017. 4

    work page 2017

  26. [26]

    Dpc: Unsupervised deep point correspondence via cross and self construction

    Itai Lang, Dvir Ginzburg, Shai Avidan, and Dan Raviv. Dpc: Unsupervised deep point correspondence via cross and self construction. In International Conference on 3D Vision (3DV), 2021. 1, 2, 3, 6

    work page 2021

  27. [27]

    The quadratic assignment problem

    Eugene L Lawler. The quadratic assignment problem. Man- agement science, 9(4):586–599, 1963. 3

    work page 1963

  28. [28]

    Deep functional maps: Structured prediction for dense shape correspondence

    Or Litany, Tal Remez, Emanuele Rodola, Alex Bronstein, and Michael Bronstein. Deep functional maps: Structured prediction for dense shape correspondence. In ICCV, 2017. 1, 2, 6

    work page 2017

  29. [29]

    Fully spectral partial shape matching

    Or Litany, Emanuele Rodol `a, Alexander M Bronstein, and Michael M Bronstein. Fully spectral partial shape matching. In Computer Graphics Forum. Wiley Online Library, 2017. 2, 7

    work page 2017

  30. [30]

    WTFM Layer: An Effective Map Ex- tractor for Unsupervised Shape Correspondence

    Shengjun Liu, Haojun Xu, Dong-Ming Yan, Ling Hu, Xinru Liu, and Qinsong Li. WTFM Layer: An Effective Map Ex- tractor for Unsupervised Shape Correspondence. Computer Graphics Forum, 2022. 2, 4

    work page 2022

  31. [31]

    Smpl: A skinned multi- person linear model

    Matthew Loper, Naureen Mahmood, Javier Romero, Gerard Pons-Moll, and Michael J Black. Smpl: A skinned multi- person linear model. ACM Transactions on Graphics (ToG), 34(6):1–16, 2015. 1

    work page 2015

  32. [32]

    Correspondence learning via linearly- invariant embedding

    Riccardo Marin, Marie-Julie Rakotosaona, Simone Melzi, and Maks Ovsjanikov. Correspondence learning via linearly- invariant embedding. NIPS, 2020. 2, 3, 6

    work page 2020

  33. [33]

    Geodesic convolutional neural net- works on riemannian manifolds

    Jonathan Masci, Davide Boscaini, Michael Bronstein, and Pierre Vandergheynst. Geodesic convolutional neural net- works on riemannian manifolds. In Proceedings of the IEEE international conference on computer vision work- shops, 2015. 1 9

    work page 2015

  34. [34]

    Shrec 2019: Matching humans with dif- ferent connectivity

    Simone Melzi, Riccardo Marin, Emanuele Rodol `a, Umberto Castellani, Jing Ren, Adrien Poulenard, Peter Wonka, and Maks Ovsjanikov. Shrec 2019: Matching humans with dif- ferent connectivity. In Eurographics Workshop on 3D Object Retrieval, 2019. 1, 5

    work page 2019

  35. [35]

    Zoomout: Spectral upsampling for efficient shape correspondence

    Simone Melzi, Jing Ren, Emanuele Rodola, Abhishek Sharma, Peter Wonka, and Maks Ovsjanikov. Zoomout: Spectral upsampling for efficient shape correspondence. arXiv preprint arXiv:1904.07865, 2019. 2, 3, 6

    work page arXiv 1904

  36. [36]

    Learning latent permutations with gumbel- sinkhorn networks

    Gonzalo Mena, David Belanger, Scott Linderman, and Jasper Snoek. Learning latent permutations with gumbel- sinkhorn networks. In ICLR, 2018. 4

    work page 2018

  37. [37]

    Informative descrip- tor preservation via commutativity for shape matching

    Dorian Nogneng and Maks Ovsjanikov. Informative descrip- tor preservation via commutativity for shape matching. In Computer Graphics Forum. Wiley Online Library, 2017. 2

    work page 2017

  38. [38]

    Functional maps: a flexible representation of maps between shapes

    Maks Ovsjanikov, Mirela Ben-Chen, Justin Solomon, Adrian Butscher, and Leonidas Guibas. Functional maps: a flexible representation of maps between shapes. ACM Transactions on Graphics (ToG), 31(4):1–11, 2012. 2, 3

    work page 2012

  39. [39]

    Fast sinkhorn filters: Using matrix scaling for non-rigid shape correspondence with functional maps

    Gautam Pai, Jing Ren, Simone Melzi, Peter Wonka, and Maks Ovsjanikov. Fast sinkhorn filters: Using matrix scaling for non-rigid shape correspondence with functional maps. In CVPR, 2021. 3

    work page 2021

  40. [40]

    Computing discrete min- imal surfaces and their conjugates

    Ulrich Pinkall and Konrad Polthier. Computing discrete min- imal surfaces and their conjugates. Experimental mathemat- ics, 2(1):15–36, 1993. 3

    work page 1993

  41. [41]

    Pointnet++: Deep hierarchical feature learning on point sets in a metric space

    Charles Ruizhongtai Qi, Li Yi, Hao Su, and Leonidas J Guibas. Pointnet++: Deep hierarchical feature learning on point sets in a metric space. NIPS, 2017. 2

    work page 2017

  42. [42]

    Structured regularization of functional map compu- tations

    Jing Ren, Mikhail Panine, Peter Wonka, and Maks Ovs- janikov. Structured regularization of functional map compu- tations. In Computer Graphics Forum. Wiley Online Library,

    work page

  43. [43]

    Continuous and orientation-preserving correspon- dences via functional maps

    Jing Ren, Adrien Poulenard, Peter Wonka, and Maks Ovs- janikov. Continuous and orientation-preserving correspon- dences via functional maps. ACM Transactions on Graphics (ToG), 37:1–16, 2018. 2, 5, 6

    work page 2018

  44. [44]

    Partial functional cor- respondence

    Emanuele Rodol `a, Luca Cosmo, Michael M Bronstein, An- drea Torsello, and Daniel Cremers. Partial functional cor- respondence. In Computer Graphics Forum. Wiley Online Library, 2017. 2, 7

    work page 2017

  45. [45]

    A scalable combinatorial solver for elastic geomet- rically consistent 3d shape matching

    Paul Roetzer, Paul Swoboda, Daniel Cremers, and Florian Bernard. A scalable combinatorial solver for elastic geomet- rically consistent 3d shape matching. In CVPR, 2022. 2

    work page 2022

  46. [46]

    Unsupervised deep learning for structured shape matching

    Jean-Michel Roufosse, Abhishek Sharma, and Maks Ovs- janikov. Unsupervised deep learning for structured shape matching. In ICCV, 2019. 2, 3, 5, 6

    work page 2019

  47. [47]

    Recent advances in shape correspon- dence

    Yusuf Sahillio ˘glu. Recent advances in shape correspon- dence. The Visual Computer, 36(8):1705–1721, 2020. 2

    work page 2020

  48. [48]

    Bending graphs: Hierarchical shape matching using gated optimal transport

    Mahdi Saleh, Shun-Cheng Wu, Luca Cosmo, Nassir Navab, Benjamin Busam, and Federico Tombari. Bending graphs: Hierarchical shape matching using gated optimal transport. In CVPR, 2022. 4

    work page 2022

  49. [49]

    Shot: Unique signatures of histograms for surface and tex- ture description

    Samuele Salti, Federico Tombari, and Luigi Di Stefano. Shot: Unique signatures of histograms for surface and tex- ture description. Computer Vision and Image Understand- ing, 125:251–264, 2014. 2

    work page 2014

  50. [50]

    Validation, comparison, and combination of algorithms for automatic detection of pulmonary nodules in computed tomography images: the luna16 challenge

    Arnaud Arindra Adiyoso Setio, Alberto Traverso, Thomas De Bel, Moira SN Berens, Cas Van Den Bogaard, Piergiorgio Cerello, Hao Chen, Qi Dou, Maria Evelina Fantacci, Bram Geurts, et al. Validation, comparison, and combination of algorithms for automatic detection of pulmonary nodules in computed tomography images: the luna16 challenge. Medi- cal image analy...

    work page 2017

  51. [51]

    Weakly supervised deep functional maps for shape matching

    Abhishek Sharma and Maks Ovsjanikov. Weakly supervised deep functional maps for shape matching. NIPS, 2020. 2, 3, 5, 6

    work page 2020

  52. [52]

    arXiv preprint arXiv:2012.00888 (2020)

    Nicholas Sharp, Souhaib Attaiki, Keenan Crane, and Maks Ovsjanikov. Diffusionnet: Discretization agnostic learning on surfaces. arXiv preprint arXiv:2012.00888, 2020. 2, 3, 4, 5

    work page arXiv 2012

  53. [53]

    A laplacian for nonman- ifold triangle meshes

    Nicholas Sharp and Keenan Crane. A laplacian for nonman- ifold triangle meshes. In Computer Graphics Forum, vol- ume 39, pages 69–80. Wiley Online Library, 2020. 3

    work page 2020

  54. [54]

    Concerning nonnegative matrices and doubly stochastic matrices

    Richard Sinkhorn and Paul Knopp. Concerning nonnegative matrices and doubly stochastic matrices. Pacific Journal of Mathematics, 21(2):343–348, 1967. 4

    work page 1967

  55. [55]

    Implicit field supervision for robust non-rigid shape match- ing

    Ramana Sundararaman, Gautam Pai, and Maks Ovsjanikov. Implicit field supervision for robust non-rigid shape match- ing. In ECCV, 2022. 2, 3, 6, 8

    work page 2022

  56. [56]

    Registration of 3d point clouds and meshes: A survey from rigid to nonrigid

    Gary KL Tam, Zhi-Quan Cheng, Yu-Kun Lai, Frank C Lang- bein, Yonghuai Liu, David Marshall, Ralph R Martin, Xian- Fang Sun, and Paul L Rosin. Registration of 3d point clouds and meshes: A survey from rigid to nonrigid. IEEE transac- tions on visualization and computer graphics , 19(7):1199– 1217, 2012. 1, 2, 3

    work page 2012

  57. [57]

    A survey on shape correspondence

    Oliver Van Kaick, Hao Zhang, Ghassan Hamarneh, and Daniel Cohen-Or. A survey on shape correspondence. In Computer Graphics Forum, 2011. 1, 2

    work page 2011

  58. [58]

    Learning from synthetic humans

    Gul Varol, Javier Romero, Xavier Martin, Naureen Mah- mood, Michael J Black, Ivan Laptev, and Cordelia Schmid. Learning from synthetic humans. In CVPR, 2017. 2, 5, 7

    work page 2017

  59. [59]

    Product manifold filter: Non-rigid shape correspondence via kernel density estima- tion in the product space

    Matthias Vestner, Roee Litman, Emanuele Rodola, Alex Bronstein, and Daniel Cremers. Product manifold filter: Non-rigid shape correspondence via kernel density estima- tion in the product space. In CVPR, 2017. 2, 3

    work page 2017

  60. [60]

    Dynamic graph cnn for learning on point clouds

    Yue Wang, Yongbin Sun, Ziwei Liu, Sanjay E Sarma, Michael M Bronstein, and Justin M Solomon. Dynamic graph cnn for learning on point clouds. ACM Transactions on Graphics (ToG), 38(5):1–12, 2019. 2

    work page 2019

  61. [61]

    Geometrically consistent elastic match- ing of 3d shapes: A linear programming solution

    Thomas Windheuser, Ulrich Schlickewei, Frank R Schmidt, and Daniel Cremers. Geometrically consistent elastic match- ing of 3d shapes: A linear programming solution. In ICCV,

    work page

  62. [62]

    Pointcontrast: Unsupervised pre- training for 3d point cloud understanding

    Saining Xie, Jiatao Gu, Demi Guo, Charles R Qi, Leonidas Guibas, and Or Litany. Pointcontrast: Unsupervised pre- training for 3d point cloud understanding. In ECCV, 2020. 5

    work page 2020

  63. [63]

    Corrnet3d: Unsupervised end-to-end learning of dense correspondence for 3d point clouds

    Yiming Zeng, Yue Qian, Zhiyu Zhu, Junhui Hou, Hui Yuan, and Ying He. Corrnet3d: Unsupervised end-to-end learning of dense correspondence for 3d point clouds. InCVPR, 2021. 1, 2, 3, 4, 6, 8 10

    work page 2021

  64. [64]

    Next, we explain de- tails on the modifications of our approach for partial shape matching

    Supplementary Document In this supplementary document we first provide more implementation details of our method. Next, we explain de- tails on the modifications of our approach for partial shape matching. Afterwards, we provide more ablative experi- ments to demonstrate the advantages of our method. Even- tually, we show additional qualitative results of o...

    work page