Fredrik Kahl

I am a professor at Chalmers University of Technology leading the Computer Vision Group. I am an applied mathematician interested in geometry, optimization, computer vision and machine learning, in particular, geometric deep learning. Current interests include equivariance, diffusion models and explainability for applications in medicine, physics and 3D scene perception.

I was previously a professor at the department of mathematics, Lund University (2006-2018) and before that, a post-doctoral fellow at the department of Computer Science, University of California San Diego (2005-2006) and at the Australian National University (2004-2005). I did my PhD at Lund University under the supervision of Profs. Anders Heyden and Gunnar Sparr (1997-2001).

Email  /  Google Scholar  /  LinkedIn  /  My homepage at Chalmers

• Open positions in my research group: PhD Student Position in Generative AI and Postdoctoral fellow in Computer Vision and Machine Learning. Deadline to apply: August 18, 2025.
• At large scale, insisting that networks rediscover known symmetries isn’t just inefficient — it’s a curious form of self-imposed ignorance! Read our latest paper on Stronger ViTs With Octic Equivariance.
• R3D2 blends 3D assets seamlessly into neural driving scenes using diffusion, unlocking scalable and realistic AD simulation. Explore the project or read the paper. Collaboration with Zenseact, UC Berkeley and Linköping University.
• Flopping for Flops is accepted to ICML 2025 in Vancouver as a spotlight paper!
• We tackle a challenging classification problem involving OOD and hierarchies. Read ProHoc: Probabilistic Hierarchical Out-of-Distribution Classification at CVPR 2025.
• Struggling with interpolating in the latent space of diffusion models? Our new paper, presented orally at SCIA 2025 in Reykjavík, may help.
• On geometric consistency for novel views in diffusion models — see our CVPR 2025 workshop paper.
• Recovering wireframe models with EdgeGaussians? Dive into our WACV 2025 paper, presented in Tucson.
• New work on privacy-preserving localization presented at 3DV 2025 in Singapore — see the paper. Collaboration with Czech Technical University in Prague.
• Equivariance and steerability for keypoint matching! Accepted as an oral at CVPR 2024 with top reviews (5,5,5). View on arXiv.
• Is it time to abandon optimization for learned Structure-from-Motion? A step in that direction: Learning SfM with Graph Attention Networks, oral at CVPR 2024.
• Serving as Area Chair for ICCV 2025 in Honolulu, CVPR 2025 in Nashville, and NeurIPS 2024 in Vancouver.

• I am the main PI for the WASP-NEST project 3D Scene Perception, Embeddings and Neural Rendering. Collaborative research project with co-PIs Kathlén Kohn and Mårten Björkman at KTH.
• Interested in the visual localization problem? We are running a benchmark site: Visual Localization. Try it out with your algorithm!
• Interested in my mathematical ancestors and descendants? You can find them here at the Mathematics Genealogy Project.
• My Erdös number is 4 via the path: Fredrik Kahl - Gunnar Sparr - Jaak Peetre - Svante Janson - Paul Erdös.
• ERC-project GlobalVision, 2008-2013. Starting Independent Research Grant, funded by the European Research Council.
• Learn more about 3D reconstruction form large-scale image sets and visit Örebro castle at the same time. For more info, read the paper. More reconstructions by Carl Olsson.
• Want to scan yourself? Read our paper CopyMe3D: Scanning and printing persons in 3D.
• Read more about my research here.

• Steerers: A framework for rotation equivariant keypoint descriptors, G Bökman, J Edstedt, M Felsberg, F Kahl
  Conference on Computer Vision and Pattern Recognition, 2024.
• Investigating how ReLU-networks encode symmetries, G Bökman, F Kahl
  Neural Information Processing Systems, 2023.
• Long-Term Visual Localization Revisited
  C Toft, W Maddern, A Torii, L Hammarstrand, E Stenborg, M Okutomi, M Pollefeys, J Sivic, T Pajdla, F Kahl, T Sattler
  IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021
• Rotation Averaging with the Chordal Distance: Global Minimizers and Strong Duality
  A Eriksson, C Olsson, F Kahl, T-J Chin
  IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021
• Tractable algorithms for robust model estimation
  O Enqvist, E Ask, F Kahl, K Åström
  International Journal of Computer Vision (IJCV), 2015
• Real-time camera tracking and 3D reconstruction using signed distance functions
  E Bylow, J Sturm, C Kerl, F Kahl, D Cremers
  Robotics: Science and Systems (RSS), 2013
• Generalized roof duality
  F Kahl, P Strandmark
  Discrete applied mathematics, 2012
• Global optimization through rotation space search
  R Hartley, F Kahl
  International Journal of Computer Vision, 2009
• Multiple-view geometry under the L_∞-norm
  F Kahl, R Hartley
  IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008
• Critical configurations for projective reconstruction from multiple views
  R Hartley, F Kahl
  International Journal of Computer Vision, 2007

For an up-to-date list of all my publications, please see my Google Scholar profile.

• Bernardo Taveiro, Computer Vision Group, Chalmers University of Technology and Zenseact AB.
• Tianyu Wu, Computer Vision Group, Chalmers University of Technology and Zenseact AB.
• David Nordström, Computer Vision Group, Chalmers University of Technology (co-supervised with Georg Bökman)
• Josef Bengtsson, Computer Vision Group, Chalmers University of Technology
• Roman Naeem, Computer Vision Group, Chalmers University of Technology (co-supervised with Lennart Svensson)
• Erik Wallin, Signal Processing Group, Chalmers University of Technology (co-supervised with Lars Hammarstrand, Lennart Svensson)
• David Hagerman Olzon, Signal Processing Group, Chalmers University of Technology (co-supervised with Lennart Svensson)

Former PhD students:

• Kunal Chelani, PhD 2025, Ericsson Research.
• Georg Bökman, PhD 2024, postdoc at Unversity of Amsterdam.
• Pavlo Melnyk, PhD 2024 from Linköping University.
• Lucas Brynte, PhD 2024, Lucid Insights AB.
• José Pedro Lopes Iglesias, PhD 2023, Apple INC.
• Fredrik Hellström, PhD 2023, postdoc at University College London.
• Carl Toft, PhD 2021, Eigenvision AB.
• Måns Larsson, PhD 2020, Eigenvision AB.
• Jennifer Alvén, PhD 2020, assistant professor at Chalmers.
• Viktor Larsson, PhD 2018, assistant professor at Lund University.
• Erik Bylow, PhD 2018, Qualcomm Inc.
• Johan Fredriksson, PhD 2016, Apple Inc.
• Matilda Landgren, PhD 2016, Cross Technology Solutions AB.
• Fangyuan Jiang, PhD 2015, self-driving car company AutoX Inc in San Jose, California.
• Linus Svärm, PhD 2015, Kiwaro AB.
• Johannes Ulén, PhD 2014, Eigenvision AB.
• Yubin Kuang, PhD 2014, co-founder of Mapillary, acquired by Facebook/Meta.
• Petter Strandmark, PhD 2013, Apple Inc.
• Olof Enqvist, PhD 2011, CEO and co-founder of Eigenvision AB.
• Martin Byröd, PhD 2010, Apple Inc.
• Klas Josephson, PhD 2010, Spiideo AB in Lund.
• Carl Olsson, PhD 2009, Professor, Lund University.
• Jan-Erik Solem, PhD 2006, CEO and co-founder of Mapillary, which was acquired by Facebook/Meta.
• Nicolas Guilbert, CEO and founder of Ange Optimization Aps.

• I am an expert at SVT Nyheter (Swedish television): Hånat filmgrepp får upprättelse med ny teknik.
• Han skapar framtidens artificiella radiologer in Elektroniktidningen.
• Snart kan AI förhindra hjärtinfarkt, Göteborgs-Posten.
• Algoritmen varnar innan hjärtinfarkten är ett faktum in forskning.se with my former PhD student Jennifer Alvén.
• Jan-Erik Solem's and my patent which was acquired by Apple reaches the news tabloids!
• We are featured in Sydsvenskan!
• Read about my ERC-project in Svenska Dagbladet.

• Several of my PhD students have received the bi-annual Best Nordic Thesis Award which I consider to be my top achievement!
  • Jennifer Alvén, Best Swedish Thesis Award 2019-2020: Combining Shape and Learning for Medical Image Analysis. Footnote: Nordic version canceled due to Covid-19 pandemic.
  • Petter Strandmark, Best Nordic Thesis Award 2013-2014: Discrete Optimization in Early Vision.
  • Carl Olsson, Best Nordic Thesis Award 2009-2010: Global Optimization in Computer Vision: Convexity, Cuts and Approximation Algorithms.
  • Jan-Erik Solem, Best Nordic Thesis Award 2005-2006: Variational Problems and Level Set Methods in Computer Vision - Theory and Applications.
  • Fredrik Kahl, Best Nordic Thesis Award 2001-2002: Geometry and Critical Configurations of Multiple Views.
• We won the Best Paper Award at ICPRAI 2024 in Jeju Island, Korea! Read the paper.
• We won the Best Industry Paper at the Swedish Symposium on Image Analysis, Göteborg, 2019 for our work on 3D Object Detection by Eskil Jörgensen, Christopher Zach and Fredrik Kahl. We get state-of-the-art results on monocular 3D object detection on Kitti! Read the paper. More videos here.
  
• We won the Best Industry Paper at the Swedish Symposium on Image Analysis, Stockholm, 2018 for our work on Visual Localization by Carl Toft et al.
• The Best Student Paper Award is awarded to "Shape-Aware Multi-Atlas Segmentation" at ICPR 2016, Cancun, Mexico! Read the paper.
• I received the Marr Prize in 2005, which is considered to be one of the most prestigious prizes in computer vision.

• I am co-founder and on the board of the computer vision consultancy Eigenvision AB.
• I am co-founder and on the board of the AI start-up Taigatech AB.
• I worked in the Management Group of CHAIR - Chalmers AI Research Centre, CHAIR, 2019-2021.
• I was on Program Management Group of WASP-AI, 2018-2020.
• The Computer Vision Group organized the Swedish Symposium on Image Analysis, March 19-20, 2019 in Göteborg.
• Tutorial in Salt Lake City at CVPR 2018 on Optimisation in Multiple View Geometry: The L-infinity Way. Tutors: Tat-Jun Chin, Anders Eriksson and Fredrik Kahl.
• Organiser of the first Swedish Symposium on Deep Learning (SSDL), June 20-21, 2017. Location: KTH, Stockholm.
• I was the main PI for the SSF project Semantic Mapping and Visual Navigation for Smart Robots a collaboration between computer vision, automatic control, machine learning and mathematics. Budget: 31.1 MSEK during 2016-2022. Funded by Swedish Foundation for Strategic Research.
• Summer School in Convex and Discrete Optimization on the island of Als, Denmark. Tutors: Fredrik Kahl and Richard Hartley, August 2015.
• Tutorial in Zurich at ECCV'14 on Robust Optimization Techniques in Computer Vision successfully completed with more than 150 registered participants. Tutors: Olof Enqvist, Fredrik Kahl and Richard Hartley.
• I was on the Editorial Board of Journal of Mathematical Imaging and Vision, 2014-2018.
• Mathematical Methods in Computer Vision, 2008-2014. A project in the programme Future Research Leaders, funded by the Swedish Foundation for Strategic Research. Read the feature article (Swedish only).
• Discrete Optimization. A PhD course in mathematics, given spring 2011.
• Optimization in Computer Vision. A one week PhD School, 19-23 May 2008 in Copenhagen, Denmark. Co-organized with Henrik Aanaes, DTU. Lectures include Prof. Richard Hartley, Phil Torr and Lieven Vanderberge.
• Want to see research in the making? .

This website is based on the source code of Jon Barron's website.