Welcome to the website of the Visual Intelligence & Perception lab at Saarland University and Max-Planck-Institute for Informatics.

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


Prof. Dr. Jan Eric Lenssen
Full Professor
Responsive image

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 with AI systems, enabling agents that are capable to perceive and act in the physical world.

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 AI algorithms that compress information from large datasets and use that information to perform inference.

We tackle algorithmic research topics in the areas of:

  • Visual and Geometric Representation Learning
  • Visual Generative Models

To advance:

  • Scene understanding and reasoning
  • Generative AI and World Modeling

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

3 papers accepted to NeurIPS 2026
September 2026
Responsive image

Happy to announce that we got three papers accepted at NeurIPS 2026. Congratulations to Gosia, Bart, Nhi and Simone, see you in Sydney, Paris, or Atlanta (who knows)!

We join Saarland University!
July 2026
Responsive image

Jan Eric Lenssen was appointed Full Professor at Saarland University. We are happy to announce that we join the University under a new name: Visual Intelligence & Perception!

Two papers accepted to ECCV 2026
June 2026
Responsive image

Happy to announce that we got two papers accepted at ECCV 2026. Congratulations to Eric, Raza and co-authors - see you in Malmö!

SemanticNVS accepted to ICML 2026
April 2026
Responsive image

Happy to announce that SemanticNVS, has been accepted to ICML 2026. Congratulations to Xinya and co-authors!

3 Papers accepted to CVPR 2026
February 2026
Responsive image

Happy to announce that we got three papers accepted at CVPR 2026. Congratulations to Asim, Yannan, Jonas, Wolfgang and co-authors - see you in Denver!

AnyUp accepted to ICLR 2026
Januar 2026
Responsive image

Happy to announce that AnyUp was accepted to ICLR 2026 as oral. Congratulations to Thomas and co-authors - see you in Rio!

DAGM German Pattern Recognition Award
September 2025
Responsive image

Jan Eric Lenssen is very honored to have received the DAGM German Pattern Recognition Award at GCPR 2025 in Freiburg last week! A big thanks goes out to all members of the group and collaborators.

NeurIPS got FLAIR!
September 2025
Responsive image

"Solving Inverse Problems with FLAIR" has been accepted at NeurIPS 2025. Big congratulations to Julius and all collaborators!

Emmy Noether Grant awarded to Jan Eric Lenssen!
July 2025
Responsive image

Very happy to announce that we have become Emmy Noether Group (Spatial Modeling and Reasoning) with potentially six years of funding from the German Research Foundation (DFG).

2 papers accepted at ICCV 2025!
July 2025
Responsive image

Two papers with people from our group have been accepted at ICCV 2025. Congratulations to first authors Xianghui and Olaf, and others!

SRMs accepted at ICML 2025!
May 2025
Responsive image

Our Spatial Reasoning Models have been accepted to ICML 2025! Congratulations to Christopher and Bart for this great achievement. See you in Vancouver!

2 papers accepted at CVPR 2025!
February 2025
Responsive image

Two of our papers, MET3R and PersonaHOI, have been accepted at CVPR 2025! Congratulations to Asim, Xinting and Haoran. See you in Nashville.

2 papers accepted at ICLR 2025!
January 2025
Responsive image

Happy to announce that two of our collaborative works, Tokenformer and ContextGNN, have been accepted at ICLR 2025!

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

CSFlow: Aligning Flow Matching with Human Contrast Sensitivity
Małgorzata Galińska, Bart Pogodzinski, Jan Eric Lenssen
CSFlow: Aligning Flow Matching with Human Contrast Sensitivity
in Neural Information Processing Systems (NeurIPS), 2026.
arXiv
TrackTok: Object-Centric Video Tokenization with Semantically Persistent Tokens
Nhi Pham, Christopher Wewer, Bernt Schiele, Jonas Fischer, Jan Eric Lenssen
TrackTok: Object-Centric Video Tokenization with Semantically Persistent Tokens
in Neural Information Processing Systems (NeurIPS), 2026.
Steering Fields: Adaptive Vector Fields for Safe Image Generation and Beyond
Simone Facchiano, Jan Eric Lenssen, Bernt Schiele, Wolfgang Stammer, Fabio Galasso, Jonas Fischer
Steering Fields: Adaptive Vector Fields for Safe Image Generation and Beyond
in Neural Information Processing Systems (NeurIPS), 2026.
All publications