Welcome to the website of the Geometric Representation Learning (GRL) group within department D2: Computer Vision and Machine Learning of the Max-Planck-Institute for Informatics.

Our research focus is on representations and algorithms for perception and inference in the 3D world, putting us at the intersection of computer vision, computer graphics and machine learning.


Research Vision

Computer vision becomes increasingly capable of representing the 3D world, given large sets of complete observations from sensors such as cameras or 3D scanners. However, in comparison with humans, we still lack an important ability: deriving complete representations from incomplete observations. Our group works towards replicating this human ability to approach the desired capabilities of a general computer vision system.

A key aspect of the human abilities is that observations we make are complemented by previously learned information: the world is not only sensed - to a large degree it is inferred. As a consequence, we approach this task by developing efficient machine learning algorithms that compress information from large datasets and use that information to perform inference.

We tackle algorithmic research topics in the areas of:

  • Efficient neural fields for volumetric representation
  • Processing of irregular structured and sparse data
  • Generative models for spatial reasoning

To advance the fields of:

  • 3D reconstruction from incomplete observation
  • Object- and scene generation
  • Scene understanding and reasoning

If you are interested to be part of the team, reach out to us directly or via the D2 application options! We offer PhD positions. We also have Master thesis topics and HiWi positions for students from University of Saarland. We do not offer short-term internships for people not already at University of Saarland.


News

2 papers accepted at 3DV 2025!
November 2024
Responsive image

Congratulations to Kevin and Xianghui for getting their great work accepted to 3DV 2025!

ECVA PhD Award!
October 2024
Responsive image

Jan Eric Lenssen is honored to receive the ECVA PhD Award at ECCV 2024 for his PhD in 2022! Congratulations!

3 papers accepted at NeurIPS 2024!
September 2024
Responsive image

We got three papers accepted at NeurIPS 2024, one on main track, and two on the datasets and benchmarks track!

2 papers accepted at ECCV 2024!
July 2024
Responsive image

We got two papers accepted at ECCV 2024! Check out the great works from Christopher and Yuanwen in Milan.

5 papers accepted to CVPR 2024!
February 2024
Responsive image

Five papers have been accepted to CVPR 2024! Big congratulations to Yannan, Philipp, Xianghui, Devi, Keyang and all the collaborators. Great work! See you in Seattle!

GRL joins VIA Center
February 2024
Responsive image

Happy to announce that D2 and GRL join the Center for Visual Computing and Artifical Intelligence (VIA), a partnership between MPI-INF and Google. Looking forward to successfull collaborations with Federico Tombaris team at Google Zürich!

Saarland/Intel Program
February 2024
Responsive image

Our project "Tractable Diffusion Models for Large-Scale 3D Scene- and Object-level Representations" was accepted and funded by the the Saarland/Intel Joint Program on the Future of Graphics and Media. We are looking forward to a successfull collaboration, in which we aim to bring generative models to efficient 3D representations!

STAR accepted at Eurographics 2024
February 2024
Responsive image

Our state of the art report about non-rigid reconstruction was accepted to Eurographics 2024. Congratulations to Raza Yunus and all collaborators!

SimNP accepted at ICCV 2023
July 2023
Responsive image

Happy to announce that our paper SimNP: Learning Self-Similarity Priors between Neural Points was accepted to ICCV 2023. We present a category-level, generalizable neural point representation that learns similarity between neural points as a prior for single- and few-view reconstruction.

Geometric Representation Learning group was founded!
June 2023
Responsive image

GRL is a group within the Computer Vision and Machine Learning department of the Max-Planck-Institute for Informatics. It is headed by Jan Eric Lenssen, a recently appointed Senior Researcher.

TU Dortmund Dissertation Award!
December 2022
Responsive image

Congratulations to Jan Eric Lenssen for winning the TU Dortmund Dissertation Award 2022.

Best Paper Honourable Mention at ECCV2022!!
Oct 2022
Responsive image

Congratulations to Garvita Tiwari, Dimitrije Antic, Jan Eric Lenssen, Nikolaos Sarafianos, Tony Tung and Gerard Pons-Moll for receiving the Best Paper Honorable Mention at ECCV'22 for the paper Pose-NDF: Modeling Human Pose Manifolds with Neural Distance Fields. 3 paper awards were given out of 6773 submissions.

Latest Publications

Spurfies: Sparse-view Surface Reconstruction using Local Geometry Priors
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.
InterTrack: Tracking Human Object Interaction without Object Templates
Xianghui Xie, Jan Eric Lenssen, Gerard Pons-Moll
InterTrack: Tracking Human Object Interaction without Object Templates
in International Conference on 3D Vision (3DV), 2025.
TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters
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.
All publications