Peter Sturm

Peter Sturm

Directeur de Recherche
STEEP research team at Inria Grenoble Rhône-Alpes
Laboratoire Jean Kuntzmann

Contact

  • INRIA Rhône-Alpes,
    655 avenue de l’Europe,
    38330 Montbonnot, France
  • peter.sturm@inria.fr
  • Phone: +33 456 527 133

 

New: From May 15 to July 4, 2019, I did a “Tour de France” by bicycle, visiting all Inria research centers to discuss about environmental issues. More here (in French only): https://project.inria.fr/inriavelo/fr/

Jump to: CV | Research/Publications | Teaching | Events | Students | Visitors

CV

See the complete CV
Short bio: Peter obtained MSc degrees from INPG (National Polytechnical Institute of Grenoble, France) and the University of Karlsruhe, both in 1994, and a PhD degree from INPG in 1997, with Long Quan as advisor. His PhD thesis was awarded the SPECIF award (given to one French PhD thesis in Computer Science per year). After a two-year post-doc at Reading University, working with Steve Maybank, he joined INRIA on a permanent research position as Chargé de Recherche in 1999. Since 2006, he is Directeur de Recherche (the INRIA equivalent of Professor). From May 2015 to September 2020, he was a Deputy Scientific Director of INRIA. In 2009/10 he spent a one-year sabbatical at CAMP, TU Munich.
Peter has been a member of programme committees for over 60 events, among which all major conferences in computer vision, image processing and pattern recognition. He was Program Chair of ICCV 2011 and RFIA 2012 and Area Chair for ECCV 2012 and 2006, ICCV 2009, CVPR 2011 and 2009, and ACCV 2010 and 2009. Peter was on the Editorial Board of IEEE Transactions on Pattern Analysis and Machine IntelligenceImage and Vision Computing JournalJournal of Mathematical Imaging and VisionJournal of Computer Science & TechnologyIPSJ (Information Processing Society of Japan) Transactions on Computer Vision and Applications, and IJICC (International Journal on Intelligent Computing and Cybernetics). He was organization co-chair of the 2008 European Conference on Computer Vision and has organized workshops and given tutorials and invited lectures at several conferences.
His main research topics have been in Computer Vision, and specifically related to camera (self-)calibration, 3D reconstruction and motion estimation, both for traditional perspective cameras and omnidirectional sensors. In 2011, Peter joined the STEEP research team, which is working towards contributing to sustainable development in general, and on the use of integrated land-use and transportation models for urban areas, in particular. This new research program concerns aspects in numerical optimization, uncertainty and sensitivity analysis for dynamical systems, applied to econometric and simulation-based models.
Since 2015, he occupies a part-time position as Deputy Scientific Director of Inria, in charge of the domain Perception, Cognition and Interaction.
During his undergraduate studies, he ran a one-person software company, within which he was mainly writing and selling software for the organization of sports events. He was involved in the organization of the 2001 Judo World Championships, the 1999 Sumo Amateur World Championships (the first ever to be held outside Japan), the 1994 Judo University World Championships, two European Championships and numerous other international and national events.

Research/Publications

Go ‎here for a list of publications or click on research topics below to se the associated publications.

  • Urban planning and related topics Our work mainly aims at contributing to sustainable development in general, and sustainable development of urban regions, in particular. This is work that started recently. We started investigating numerical algorithms for instantiating and validating integrated models for land use and transportation. Other works concern the study of urban sprawl, land cover changes, and material flows.
  • 3D scene modelling Our main motivations are twofold: (i) study representations and develop algorithms suitable for obtaining good quality 3D models. (ii) do so by starting to reason from first principles. As for the latter aspect, we started our work by re-visiting what photoconsistency measure should be used for multi-view stereo and other 3D modeling problems: one aims at estimating a 3D model (plus, possibly, appearance or even lighting) whose renderings from the viewpoints of the input images, results in images that are as close to the acquired ones, as possible. This is easy to state, but the corresponding cost function is actually rather hard to optimize. One of our main contributions is to derive the gradient of this type of cost function, see Gargallo et al. 2007 and Delaunoy et al. 2008 below.
  • Joint modelling of geometry, reflectance and/or illumination Images of objects are the result of an interplay between object shape and appearance, lighting, and camera properties (geometry and radiometry). Ideally, one would like to recover all of these from images, but this is obviously highly ill-posed in general. We were interested in exploring several directions in the continuum of this geometry – appearance – lighting problem. One direction has been the joint estimation of shape and appearance for non-Lambertian surfaces, using images acquired under controlled lighting. Other directions have been the recovery of lighting conditions or radiometric calibration, from unstructured image collections. I think that there is lots of room for future work on the geometry – appearance – lighting continuum.
  • Reconstruction and detection of specular or refractive surfaces Related to the previous topic, but less appearance and more geometry-oriented. It started with the reconstruction of perfectly specular objects (mirrors) and lead to working on the detection and the 3D reconstruction of semi-transparent surfaces (reflective plus refractive).
  • Omnidirectional vision and generic camera models Our main motivation was to derive theories and algorithms for 3D vision, that are applicable to whatever camera, be it a “regular” camera, a catadioptric one, a fish-eye device, etc. This was achieved for the problems of camera calibration, pose estimation, motion estimation, 3D reconstruction, and also for self-calibration. Also, check out our monograph on all kinds of camera models that have been proposed in the literature: Sturm et al. 2011, with more than 500 references.
  • 3D reconstruction using geometric constraints Older work that explored two main directions: (i) interactive 3D modeling, where the user provides simple geometric constraints (parallelism of lines, coplanarity of points, etc.) that may even enable 3D reconstruction from a single image. (ii) use such constraints to increase accuracy in multi-view 3D reconstruction.
  • Camera calibration Our work on calibration (of perspective cameras) includes the first peer-reviewed publication of the popular plane-based calibration approach (that is for example contained in OpenCV), as well as contributions to the calibration of multi-camera systems and several special cases (calibration from images of circles, of one-dimensional objects, …).
  • Self-calibration and critical motions Older work, most of it done during and shortly after my PhD. The main contribution is a theoretical study of degeneracies of the self-calibration problem: in a nutshell, it turned out that the most “natural” camera motions (e.g. turning around an object along a circle) are “worst” for self-calibration feasibility or accuracy. This work explains why self-calibration was originally deemed highly unstable and allows to define guidelines for image acquisitions that are favorable for self-calibration (interestingly, these guidelines are commonplace in photogrammetry, where they seem to have been derived more empirically). Other works on self-calibration includes algorithms for self-calibration of cameras by taking images of a planar object, with otherwise unknown structure.
  • Structure from motion for lines A rather complete treatment of structure from motion (motion estimation, triangulation, bundle adjustment) for line features, as opposed to the more well-studied point features.
  • Triangulation of points Our main contribution here is the first globally optimal method for triangulating 3D points from correspondences in two images.
  • Projective reconstruction We have extended the classical Tomasi-Kanade factorization approach for jointly estimating object shape and camera motion, from the affine / orthographic camera model to the perspective one.
  • Object detection and tracking I have also worked a little on object detection and tracking, among others on tracking using particle filters.
  • Image registration and deblurring Our main set of works concerns the problem of registering multispectral pushbroom images acquired by spaceborne cameras, for image mosaicing as well as high-accuracy estimation of a satellite’s orientation along time.
  • Projector-camera systems Our works concerns the (self-)calibration of projector-camera systems and the usage of these for one-shot (i.e. instantaneous) object scanning.
  • Model selection for two view geometry During my post-doc, Steve Maybank and I did some trials on rigorously applying the MDL principle for model selection in two view geometry (e.g. selecting between a fundamental matrix and a homography, given a set of point matches).
  • Other structure from motion work A mix of works, ranging from pose estimation to structure from motion for dynamic scenes to the study of the impact of an inaccurate camera calibration on the accuracy of motion estimation, etc. Check out my article and associated talk, that summarize some current findings of a deep literature study on the history of 3D vision (more to come, one day…): Sturm 2011.
  • PhD and Habilitation theses

Teaching

Events I am or have been involved in

2019:

2018:

2017:

2016:

2015:

2014:

2013:

2012:

2011:

2010:

On February 16, I resigned from my appointment as Program Chair. Click here to find out why. 2009:

2008:

2007:

2006:

2005:

Students, Post-docs, Engineers
  • Joanna Maurin, Intern (2020)
  • Olivier Mauviel, MSc project (2020)
  • Valentin Guimont, MSc project (2020)
  • Samba Diop, MSc project (2018)
  • Lucas Rezakhanlou, Intern (2017)
  • Emna Jribi, Engineer (2016/17)
  • Songyou Peng, Intern (2016 and 17)
  • Julien Armand, Intern (2015/16)
  • Huu Phuoc Nguyen, Intern (2015/16)
  • Martí Bosch, MSc project (2015/16)
  • Luciano Gervasoni, Intern (2014), PhD student (2015-18)
  • Fausto Lo Feudo, Post-doc (2015-19)
  • Thomas Capelle, PhD student (2013-17), Post-doc (2017/18)
  • Solange Blundi, Intern (2014)
  • Patrizio Inzaghi, Intern (2014)
  • Abdelrahman Mohamed Ahmed, Intern (2014)
  • Brinduša Smaranda, MSc project (2013)
  • Jakub Krzywda, Intern (2013)
  • Alejandro Deymonnaz, Engineer (2012)
  • Saurabh Sensharma, Intern (2009)
  • Prakhar Biyani, Intern (2009)
  • Ashutosh Natraj, PhD thesis (with Université de Picardie Jules Verne, 2009-2012)
  • Visesh Chari, PhD thesis (2008-2012)
  • Varun Raj Kompella, MSc project (2008-09)
  • Simone Gasparini, Post-doc (2007-11)
  • Jamil Draréni, PhD thesis (with Université de Montréal, 2007-11)
  • José Manuel Fernandez, MSc thesis (2008)
  • Régis Perrier, PhD thesis (2007-11)
  • Mauricio Diaz, PhD thesis (2007-11)
  • Amaël Delaunoy, PhD thesis (2007-11)
  • Kuk-Jin Yoon, Post-doc (2006-08)
  • Yoo-Jin Choi, Intern (2006-07)
  • Pau Gargallo, MSc project (2002-03), PhD thesis (2003-08)
  • Aude Jacquot, PhD thesis (2003-06)
  • Srikumar Ramalingam, PhD thesis (2004-06)
  • Thomas Bonfort, MSc project (2001-02), PhD thesis (2002-06)
  • Marta Wilczkowiak, MSc project (1999-2000), PhD thesis (2000-04)
  • Dana Cobzas, Post-doc (2004-05)
  • Adrien Bartoli, MSc project (1999-2000), PhD thesis (2000-03)
  • Salvatore Notarangelo, BSc project (2002-03)
  • Lucile Prin-Zanet, MSc project (2002-03)
  • Anthony Garcia, BSc project (2001-02)
  • Madgalena Urbanek, BSc project (1999-2000), MSc project (2000-01)
  • Laurent Verschueren, MSc project (2000)
  • Matthieu Personnaz, Engineer (2000-03)
  • Frank Althoff, BSc project (1996)

Visitors
  • Byung-Kuk Seo, Fraunhofer Institute, Darmstadt, Germany, 2015.
  • Juho Kannala, University of Oulu, Finland, 2011-12
  • João Barreto, University of Coimbra, Portugal, 2009
  • Julian Quiroga, Universidad Javeriana, Bogotá, Colombia, 2009
  • Hiroshi Kawasaki, Saitama University, Japan, 2009-10
  • Sacha Bernet, Université de Haute-Alsace, Mulhouse, France, 2009
  • Yalin Bastanlar, Middle East Technical University, Ankara, Turkey, 2008
  • Luis Puig, Universidad de Zaragoza, Spain, 2008
  • Josechu Guerrero Campo, Universidad de Zaragoza, Spain, 2007
  • Olivier Koch, MIT, 2007
  • Carlos Torre Ferrero, Universidad de Cantabria, Santander, Spain, 2007
  • Mauricio Diaz, Universidad Javeriana, Bogotá, Colombia, 2007
  • Dana Cobzas, University of Alberta, Edmonton, Canada (2007)
  • Martin Jägersand, University of Alberta, Edmonton, Canada (2007)
  • José Gaspar, Instituto Superior Técnico of Lisbon, Portugal, 2006
  • Kiyoung Kim, GIST (Gwangju Institute of Science and Technology), South Korea, 2005-06
  • Lazaros Grammatikopoulos, National Technical University Athens, Greece, 2005
  • Diego Aguilera, Universidad de Salamanca, Spain, 2005
  • Jean-Philippe Tardif, Université de Montréal, Canada, 2005 and 2006
  • Tomislav Pribanić, University of Zagreb, Croatia, 2004
  • Pär Hammarstedt, Malmö University, Sweden, 2004
  • Ferran Espuny, UPC Barcelona, 2004 and 2006
  • Tomáš Svoboda, Czech Technical University, Prague, 1996

Comments are closed.