Geometric Deep Learning
Research Grants
KI-Starter from the Ministry for Culture and Science NRW ‘Robust Geometric Deep Learning’ (2022-2024)
Publications
Synchronous Diffusion for Unsupervised Smooth Non-Rigid 3D Shape Matching
Dongliang Cao, Zorah Lähner, Florian Bernard
Published in European Conference on Computer Vision (ECCV) (Accepted), 2024
[bibtex]
3D Shape Completion with Test-Time Training
Michael Schopf-Kuester, Zorah Lähner, Michael Moeller
Published in ICLR Workshop on Geometry-Grounded Representation Learning and Generative Modeling (GRaM), 2024
[bibtex]
Implicit-ARAP: Efficient Handle-Guided Deformation of High-Resolution Meshes and Neural Fields via Local Patch Meshing
Daniele Baieri, Filippo Maggioli, Zorah Lähner, Simone Melzi, Emanuele Rodolà
Published in arXiv:2405.12895, 2024
[arxiv] [bibtex]
Hybrid Functional Maps for Crease-Aware Non-Isometric Shape Matching
Lennart Bastian*, Yizheng Xie*, Nassir Navab, Zorah Lähner
Published in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024
[arxiv] [bibtex]
On the Direct Alignment of Latent Spaces
Zorah Lähner, Michael Moeller
Published in NeuRIPS Workshop on Unifying Representations in Neural Models (UniReps), 2023
[pdf] [bibtex]
Kissing to Find a Match: Efficient Low-Rank Permutation Representation
Hannah Dröge, Zorah Lähner, Yuval Bahat, Onofre Martorell, Felix Heide, Michael Moeller
Published in Neural Information Processing Systems (NeuRIPS), 2023
[pdf] [arxiv] [github] [bibtex]
A Network Analysis for Correspondence Learning via Linearly-Embedded Functions
Sharik Siddiqi, Zorah Lähner
Published in German Conference on Pattern Recognition (GCPR), 2023
[pdf] [bibtex]
A Simple Strategy to Make Neural Networks Provably Invariant
Kanchana Vaishnavi Gandikota, Jonas Geiping, Zorah Lähner, Adam Czapliński, Michael Moeller
Published in Asian Conference on Computer Vision (ACCV), 2022
[pdf] [arxiv] [bibtex]
Intrinsic Neural Fields: Learning Functions on Manifolds
Lukas Koestler, Daniel Grittner, Michael Moeller, Daniel Cremers, Zorah Lähner
Published in European Conference on Computer Vision (ECCV), 2022
[pdf] [arxiv] [github] [bibtex]
Unsupervised Dense Shape Correspondence using Heat Kernels
Mehmet Aygün, Zorah Lähner, Daniel Cremers
Published in Conference on 3D Vision (3DV), 2020
[pdf] [arxiv] [bibtex]
DeepWrinkles: Accurate and Realistic Clothing Modeling
Zorah Lähner, Daniel Cremers, Tony Tung
Published in European Conference on Computer Vision (ECCV), 2018
[pdf] [arxiv] [video] [bibtex]