- Max-Planck-Institut für Informatik
Saarland Informatics Campus
Campus E1 4
66123 Saarbrücken - Room 618
- jlenssen@mpi-inf.mpg.de
About Me
Personal page.
My interest lies in designing differentiable algorithms, architectures and representations for percieving and representing the 3D world. Past research includes works in the areas of graph neural networks, equivariant operators, implicit neural fields and differentiable eigendecomposition. Currently, I am interested in scalable (generative) modeling for 3D representations, reconstruction and reasoning across spatial domains.
Short Biography
- Heading the Geometric Representation Learning Group at MPI-INF
- Founding team member of Kumo.ai (Stanford / TU Dortmund startup), bringing GNNs to relational data.
- ELLIS Unit Faculty Member and Saarland Informatics Campus Fellow.
- Research internships at Facebook (Meta) Reality Labs and Nnaisense.
- Dr.-Ing. in Computer Science (Feb. 2022) from TU Dortmund University under Heinrich Müller.
Community
- Area Chair for NeurIPS 2024, ICLR 2025 and CVPR 2025
- Reviewer for NeurIPS 2019-2023, ICLR 2021-2024, CVPR 2023-2024, ECCV 2022-2024, ICCV 2023, 3DV 2023, 2025, TPAMI, SIGGRAPH Asia 2024
Awards and Nominations
- ECVA PhD Award for 2022 at ECCV 2024
- TU Dortmund Dissertation Award 2022
- ECCV 2022 Best Paper Honorable Mention
- CVPR 2020 Best Paper Nomination
- Best Paper Award at BIOSIGNALS 2018
- Outstanding Reviewer Awards at CVPR 2024 and NeurIPS 2019
Publications
Kevin Raj,
Christopher Wewer,
Raza Yunus,
Eddy Ilg,
Jan Eric Lenssen
Spurfies: Sparse-view Surface Reconstruction using Local Geometry Priors
in International Conference on 3D Vision (3DV), 2025.
Spurfies: Sparse-view Surface Reconstruction using Local Geometry Priors
in International Conference on 3D Vision (3DV), 2025.
Xianghui Xie,
Jan Eric Lenssen,
Gerard Pons-Moll
InterTrack: Tracking Human Object Interaction without Object Templates
in International Conference on 3D Vision (3DV), 2025.
InterTrack: Tracking Human Object Interaction without Object Templates
in International Conference on 3D Vision (3DV), 2025.
Haiyang Wang,
Yue Fan,
Muhammad Ferjad Naeem,
Yongqin Xian,
Jan Eric Lenssen,
Liwei Wang,
Federico Tombari,
Bernt Schiele
TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters
in arXiv preprint, 2024.
TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters
in arXiv preprint, 2024.
Yuanwen Yue,
Anurag Das,
Francis Engelmann,
Siyu Tang,
Jan Eric Lenssen
Improving 2D Feature Representations by 3D-Aware Fine-Tuning
in European Conference on Computer Vision (ECCV), 2024.
Improving 2D Feature Representations by 3D-Aware Fine-Tuning
in European Conference on Computer Vision (ECCV), 2024.
Christopher Wewer,
Kevin Raj,
Eddy Ilg,
Bernt Schiele,
Jan Eric Lenssen
latentSplat: Autoencoding Variational Gaussians for Fast Generalizable 3D Reconstruction
in European Conference on Computer Vision (ECCV), 2024.
latentSplat: Autoencoding Variational Gaussians for Fast Generalizable 3D Reconstruction
in European Conference on Computer Vision (ECCV), 2024.
Joshua Robinson,
Rishabh Ranjan,
Weihua Hu,
Kexin Huang,
Jiaqi Han,
Alejandro Dobles,
Matthias Fey,
Jan Eric Lenssen,
Yiwen Yuan,
Zecheng Zhang,
Xinwei He,
Jure Leskovec
RelBench: A Benchmark for Deep Learning on Relational Databases
in NeurIPS 2024 - Dataset and Benchmarks, 2024.
RelBench: A Benchmark for Deep Learning on Relational Databases
in NeurIPS 2024 - Dataset and Benchmarks, 2024.
Wolfgang Boettcher,
Lukas Hoyer,
Ozan Unal,
Jan Eric Lenssen,
Bernt Schiele
Scribbles for All - Benchmarking Scribble Supervised Segmentation Across Datasets
in NeurIPS 2024 - Dataset and Benchmarks, 2024.
Spotlight
Scribbles for All - Benchmarking Scribble Supervised Segmentation Across Datasets
in NeurIPS 2024 - Dataset and Benchmarks, 2024.
Spotlight
Devikalyan Das,
Christopher Wewer,
Raza Yunus,
Eddy Ilg,
Jan Eric Lenssen
Neural Parametric Gaussians for Monocular Non-Rigid Object Reconstruction
in Conference on Computer Vision and Pattern Recognition (CVPR), 2024.
Neural Parametric Gaussians for Monocular Non-Rigid Object Reconstruction
in Conference on Computer Vision and Pattern Recognition (CVPR), 2024.
Jialin Chen,
Jan Eric Lenssen,
Aosong Feng,
Weihua Hu,
Matthias Fey,
Leandros Tassiulas,
Jure Leskovec,
Rex Ying
From Similarity to Superiority: Channel Clustering for Time Series Forecasting
in Neural Information Processing Systems (NeurIPS), 2024.
From Similarity to Superiority: Channel Clustering for Time Series Forecasting
in Neural Information Processing Systems (NeurIPS), 2024.
Xianghui Xie,
Bharat Bhatnagar,
Jan Eric Lenssen,
Gerard Pons-Moll
Template Free Reconstruction of Human-object Interaction with Procedural Interaction Generation
in Conference on Computer Vision and Pattern Recognition (CVPR), 2024.
Highlight
Template Free Reconstruction of Human-object Interaction with Procedural Interaction Generation
in Conference on Computer Vision and Pattern Recognition (CVPR), 2024.
Highlight
Yannan He,
Garvita Tiwari,
Tolga Birdal,
Jan Eric Lenssen,
Gerard Pons-Moll
NRDF: Neural Riemannian Distance Fields for Learning Articulated Pose Priors
in Conference on Computer Vision and Pattern Recognition (CVPR), 2024.
Highlight
NRDF: Neural Riemannian Distance Fields for Learning Articulated Pose Priors
in Conference on Computer Vision and Pattern Recognition (CVPR), 2024.
Highlight
Keyang Zhou,
Bharat Bhatnagar,
Jan Eric Lenssen,
Gerard Pons-Moll
GEARS: Local Geometry-aware Hand-object Interaction Synthesis
in Conference on Computer Vision and Pattern Recognition (CVPR), 2024.
GEARS: Local Geometry-aware Hand-object Interaction Synthesis
in Conference on Computer Vision and Pattern Recognition (CVPR), 2024.
Philipp Schröppel,
Christopher Wewer,
Jan Eric Lenssen,
Eddy Ilg,
Thomas Brox
Neural Point Cloud Diffusion for Disentangled 3D Shape and Appearance Generation
in Conference on Computer Vision and Pattern Recognition (CVPR), 2024.
Neural Point Cloud Diffusion for Disentangled 3D Shape and Appearance Generation
in Conference on Computer Vision and Pattern Recognition (CVPR), 2024.
Raza Yunus,
Jan Eric Lenssen,
Michael Niemeyer,
Yiyi Liao,
Christian Rupprecht,
Christian Theobalt,
Gerard Pons-Moll,
Jia-Bin Huang,
Vladislav Golyanik,
Eddy Ilg
Recent Trends in 3D Reconstruction of General Non-Rigid Scenes
in Eurographics, 2024.
Recent Trends in 3D Reconstruction of General Non-Rigid Scenes
in Eurographics, 2024.
Matthias Fey,
Weihua Hu,
Kexin Huang,
Jan Eric Lenssen,
Rishabh Ranjan,
Joshua Robinson,
Rex Ying,
Jiaxuan You,
Jure Leskovec
Relational Deep Learning: Graph Representation Learning on Relational Databases
in International Conference on Machine Learning (ICML) - Position Papers, 2024.
Relational Deep Learning: Graph Representation Learning on Relational Databases
in International Conference on Machine Learning (ICML) - Position Papers, 2024.
Christopher Wewer,
Eddy Ilg,
Bernt Schiele,
Jan Eric Lenssen
SimNP: Learning Self-Similarity Priors between Neural Points
in International Conference of Computer Vision (ICCV), 2023.
SimNP: Learning Self-Similarity Priors between Neural Points
in International Conference of Computer Vision (ICCV), 2023.
Garvita Tiwari,
Dimitrije Antic,
Jan Eric Lenssen,
Nikolaos Sarafianos,
Tony Tung,
Gerard Pons-Moll
Pose-NDF: Modeling Human Pose Manifolds with Neural Distance Fields
in European Conference on Computer Vision (ECCV), 2022.
Oral - Best Paper Honourable Mention
Pose-NDF: Modeling Human Pose Manifolds with Neural Distance Fields
in European Conference on Computer Vision (ECCV), 2022.
Oral - Best Paper Honourable Mention
Keyang Zhou,
Bharat Lal Bhatnagar,
Jan Eric Lenssen,
Gerard Pons-Moll
TOCH: Spatio-Temporal Object-to-Hand Correspondence for Motion Refinement
in European Conference on Computer Vision (ECCV), 2022.
TOCH: Spatio-Temporal Object-to-Hand Correspondence for Motion Refinement
in European Conference on Computer Vision (ECCV), 2022.
Matthias Fey,
Jan Eric Lenssen,
Frank Weichert,
Jure Leskovec
GnnAutoScale: Scalable and Expressive Graph Neural Networks via Historical Embeddings
in International Conference of Machine Learning (ICML), 2021.
GnnAutoScale: Scalable and Expressive Graph Neural Networks via Historical Embeddings
in International Conference of Machine Learning (ICML), 2021.
Matthias Fey,
Jan Eric Lenssen,
Christopher Morris,
Jonathan Masci,
Nils Kriege
Deep Graph Matching Consensus
in International Conference on Learning Representations (ICLR), 2020.
Deep Graph Matching Consensus
in International Conference on Learning Representations (ICLR), 2020.
Jan Eric Lenssen,
Christian Osendorfer,
Jonathan Masci
Deep Iterative Surface Normal Estimation
in Conference on Computer Vision and Pattern Recognition (CVPR), 2020.
Oral - Best Paper Nominated
Deep Iterative Surface Normal Estimation
in Conference on Computer Vision and Pattern Recognition (CVPR), 2020.
Oral - Best Paper Nominated
Rohan Chabra,
Jan Eric Lenssen,
Eddy Ilg,
Tanner Schmidt,
Julian Straub,
Steven Lovegrove,
Richard Newcombe
Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstruction
in European Conference on Computer Vision (ECCV), 2020.
Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstruction
in European Conference on Computer Vision (ECCV), 2020.
Yongheng Zhao,
Tolga Birdal,
Jan Eric Lenssen,
Emanuele Menegatti,
Leonidas Guibas,
Federico Tombari
Quaternion Equivariant Capsule Networks for 3D Point Clouds
in European Conference on Computer Vision (ECCV), 2020.
Oral
Quaternion Equivariant Capsule Networks for 3D Point Clouds
in European Conference on Computer Vision (ECCV), 2020.
Oral
Matthias Fey,
Jan Eric Lenssen
Fast Graph Representation Learning with PyTorch Geometric
in ICLR Workshop on Graph Learning (ICLR-W), 2019.
Fast Graph Representation Learning with PyTorch Geometric
in ICLR Workshop on Graph Learning (ICLR-W), 2019.
Christopher Morris,
Martin Ritzert,
Matthias Fey,
William Hamilton,
Jan Eric Lenssen,
Gaurav Rattan,
Martin Grohe
Weisfeiler and leman go neural: Higher-order graph neural networks
in AAAI Conference on Artificial Intelligence (AAAI), 2019.
Weisfeiler and leman go neural: Higher-order graph neural networks
in AAAI Conference on Artificial Intelligence (AAAI), 2019.
Jan Eric Lenssen,
Matthias Fey,
Pascal Libuschewski
Group Equivariant Capsule Networks
in Neural Information Processing Systems (NeurIPS), 2018.
Group Equivariant Capsule Networks
in Neural Information Processing Systems (NeurIPS), 2018.