Laura Leal-Taixé

Rudolf Mößbauer Tenure Track

Technical University of Munich


Focus Group/Research Project
Dynamic Vision and Learning

Short CV

Prof. Dr.-Ing. Laura Leal-Taixé was born in Barcelona where she pursued B.Sc. and M.Sc. degrees in Telecommunications Engineering at the Technical University of Catalonia (UPC). She went to Boston, USA to do her Master’s thesis at Northeastern University with a fellowship from the Vodafone foundation. She worked on computer vision and image processing for medical images. From 2009 until 2013, she worked towards her PhD degree at the Institute for Information Processing (TNT) of the Leibniz University of Hannover in Germany. She focused on topics such as multiple people tracking, object detection, pose estimation. She graduated in February 2014, presenting the thesis “Multiple people tracking with context awareness”. During her PhD, she was at the University of Michigan, Ann Arbor, USA, for one year as a visiting scholar with Prof. Silvio Savarese. She then spent two years as a postdoctoral researcher at the Institute for Geodesy and Photogrammetry at ETH Zürich, Switzerland, working on tracking and benchmarking.

In May 2016, she moved to Munich where she started working at the Computer Vision Group as a senior postdoctoral researcher.

She is currently as Professor at the Dynamic Vision and Learning group after receiving a Sofja Kovalevskaja Award of 1.65 million euros for her project socialMaps.

Selected Awards

  • 2017, Sofja Kovalevskaja Award, 1.65 million euros, Humboldt Foundation
  • 2017, DAAD Funding, Australia-German Joint Research Corporation Scheme
  • 2016, Travel grant awarded by the Women in Computer Vision Association at CVPR
  • 2013, Travel grant awarded for the Doctoral Consortium at CVPR
  • 2008, Vodafone scholarship to pursue the Master Thesis in the USA

Research Interests

Prof. Dr.-Ing. Laura Leal-Taixé (b. 1984) conducts research in the area of Computer Vision and Machine Learning. In particular, she focuses on video analysis, solving tasks such as multiple object tracking, motion analysis or semantic segmentation. Allowing machines to automatically analyse video data is essential for applications such as Autonomous Driving.

During her doctoral studies, she focused on including social and multi-view information into optimization schemes for multiple pedestrian tracking. She later moved towards Machine Learning and how to better adapt learning algorithms such as neural networks to work on video streams.

In the project socialMaps, for which she has been granted a Sofja Kovalevskaja Award, she proposes to include dynamic and social information into static maps, so as to decouple vehicle traffic from pedestrian traffic.

Selected Publications

  • Fenzi, Michele; Leal-Taixe, Laura; Ostermann, Jorn; Tuytelaars, Tinne: Continuous Pose Estimation with a Spatial Ensemble of Fisher Regressors. 2015 IEEE International Conference on Computer Vision (ICCV), IEEE, 2015
  • Milan, Anton; Leal-Taixe, Laura; Schindler, Konrad; Reid, Ian: Joint tracking and segmentation of multiple targets. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, 2015 
  • Leal-Taixe, Laura; Fenzi, Michele; Kuznetsova, Alina; Rosenhahn, Bodo; Savarese, Silvio: Learning an Image-Based Motion Context for Multiple People Tracking. 2014 IEEE Conference on Computer Vision and Pattern Recognition, IEEE, 2014 
  • Fenzi, Michele; Leal-Taixe, Laura; Rosenhahn, Bodo; Ostermann, Jorn: Class Generative Models Based on Feature Regression for Pose Estimation of Object Categories. 2013 IEEE Conference on Computer Vision and Pattern Recognition, IEEE, 2013
  • Leal-Taixe, Laura; Pons-Moll, G.; Rosenhahn, B.: Branch-and-price global optimization for multi-view multi-target tracking. 2012 IEEE Conference on Computer Vision and Pattern Recognition, IEEE, 2012 
  • Leal-Taixe, Laura; Pons-Moll, Gerard; Rosenhahn, Bodo: Everybody needs somebody: Modeling social and grouping behavior on a linear programming multiple people tracker. 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops), IEEE, 2011

Publications as TUM-IAS-Fellow


  • Ismail Elezi, Sebastiano Vascon, Alessandro Torcinovich, Marcello Pelillo, Laura Leal-Taixe: The Group Loss for Deep Metric Learning. 2019 mehr… BibTeX
  • Kishan Sharma, Moritz Gold, Christian Zurbruegg, Laura Leal-Taixé, Jan Dirk Wegner: HistoNet: Predicting size histograms of object instances. 2019 mehr… BibTeX
  • Maxim Maximov, Laura Leal-Taixé, Mario Fritz, Tobias Ritschel: Deep Appearance Maps. 2019 mehr… BibTeX
  • Patrick Dendorfer, Hamid Rezatofighi, Anton Milan, Javen Shi, Daniel Cremers, Ian Reid, Stefan Roth, Konrad Schindler, Laura Leal-Taixe: CVPR19 Tracking and Detection Challenge: How crowded can it get? 2019 mehr… BibTeX
  • Philipp Bergmann, Tim Meinhardt, Laura Leal-Taixe: Tracking without bells and whistles. 2019 mehr… BibTeX
  • Qadeer Khan, Patrick Wenzel, Daniel Cremers, Laura Leal-Taixé: Towards Generalizing Sensorimotor Control Across Weather Conditions. 2019 mehr… BibTeX
  • Qunjie Zhou, Torsten Sattler, Marc Pollefeys, Laura Leal-Taixe: To Learn or Not to Learn: Visual Localization from Essential Matrices. 2019 mehr… BibTeX
  • Torsten Sattler, Qunjie Zhou, Marc Pollefeys, Laura Leal-Taixe: Understanding the Limitations of CNN-based Absolute Camera Pose Regression. 2019 mehr… BibTeX


  • Laude, Emanuel; Lange, Jan-Hendrik; Schupfer, Jonas; Domokos, Csaba; Leal-Taixe, Laura; Schmidt, Frank R.; Andres, Bjoern; Cremers, Daniel: Discrete-Continuous ADMM for Transductive Inference in Higher-Order MRFs. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, IEEE, 2018 mehr… BibTeX Volltext ( DOI )
  • Mengyu Chu, You Xie, Jonas Mayer, Laura Leal-Taixé, Nils Thuerey: Learning Temporal Coherence via Self-Supervision for GAN-based Video Generation. 2018 mehr… BibTeX
  • Ochs, Peter; Meinhardt, Tim; Leal-Taixe, Laura; Moeller, Michael: Lifting Layers: Analysis and Applications. In: Computer Vision – ECCV 2018. Springer International Publishing, 2018 mehr… BibTeX Volltext ( DOI )
  • S. Hamid Rezatofighi, Roman Kaskman, Farbod T. Motlagh, Qinfeng Shi, Daniel Cremers, Laura Leal-Taixé, Ian Reid: Deep Perm-Set Net: Learn to predict sets with unknown permutation and cardinality using deep neural networks. 2018 mehr… BibTeX


  • Caelles, S.; Maninis, K. -K.; Pont-Tuset, J.; Leal-Taixe, L.; Cremers, D.; Gool, L. Van: One-Shot Video Object Segmentation. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, 2017 mehr… BibTeX Volltext ( DOI )
  • Walch, F.; Hazirbas, C.; Leal-Taixe, L.; Sattler, T.; Hilsenbeck, S.; Cremers, D.: Image-Based Localization Using LSTMs for Structured Feature Correlation. 2017 IEEE International Conference on Computer Vision (ICCV), IEEE, 2017 mehr… BibTeX Volltext ( DOI )