PeopleofSuperintelligence

Researcher

Michael Calonder

Michael Calonder is a data scientist and machine learning engineer whose BRIEF descriptor describes image feature points with binary strings that are very fast to build and to match. In 2006, he published work through ETH Zurich on evolutionary algorithms for gene expression data. With Vincent Lepetit and Pascal Fua he developed keypoint signatures in 2008 and compact signatures in 2009, and in 2010 he coauthored View-based maps with Kurt Konolige and others in The International Journal of Robotics Research. He presented BRIEF at ECCV 2010, defended his EPFL doctoral thesis on high-speed interest point matching under Fua in October 2010, and published a journal paper on BRIEF in July 2012. The original BRIEF paper received the Koenderink Prize in 2020.

Works
20
Citations
5,562
h-index
8

Publication numbers from OpenAlex, as of 22 October 2026.

Timeline

  1. 2006

    Evolutionary algorithms at ETH Zurich

    ETH Zurich publishes his 2006 work on multi-objective clustering of gene expression data with evolutionary algorithms, using a query gene approach. With S. Bleuler and E. Zitzler, he coauthors a 2006 paper at the International Conference on Parallel Problem Solving from Nature on identifying gene modules in heterogeneous biological data with multiobjective evolutionary algorithms.

  2. 2008

    Keypoint signatures at ECCV

    At ECCV 2008, he presents Keypoint Signatures for Fast Learning and Recognition with Vincent Lepetit and Pascal Fua. The descriptor characterizes a keypoint by its response to Randomized Tree classifiers, can be learned online for tasks such as SLAM, and has discriminative power comparable to the slower SIFT descriptor.

  3. 2009–2010

    Compact signatures and View-based maps

    At ICCV 2009, he presents Compact Signatures for High-Speed Interest Point Description and Matching with Vincent Lepetit, Pascal Fua, Kurt Konolige, James Bowman and Patrick Mihelich, aimed at classifier-based signatures whose large memory needs suit low-memory devices poorly. With Konolige, Bowman, J. D. Chen, Mihelich and others, he coauthors View-based maps in The International Journal of Robotics Research in 2010.

  4. 2010

    BRIEF at ECCV 2010

    With Vincent Lepetit, Christoph Strecha and Pascal Fua, he presents BRIEF at ECCV 2010, a feature point descriptor built from binary strings and simple intensity difference tests and compared with the Hamming distance. BRIEF is very fast to build and to match, and it matches or beats SURF and U-SURF on standard benchmarks in a fraction of their time.

  5. October 2010

    Doctorate under Pascal Fua

    He defends his EPFL doctoral thesis in computer science, Robust, High-Speed Interest Point Matching for Real-Time Applications, in October 2010, with Pascal Fua as thesis director.

  6. July 2012

    BRIEF in IEEE TPAMI

    In July 2012, he publishes BRIEF: Computing a Local Binary Descriptor Very Fast in IEEE Transactions on Pattern Analysis and Machine Intelligence, with Vincent Lepetit, Mustafa Ozuysal, Tomasz Trzciński, Christoph Strecha and Pascal Fua.

  7. 2020

    The Koenderink Prize

    His ECCV 2010 paper BRIEF: Binary Robust Independent Elementary Features, written with Vincent Lepetit, Christoph Strecha and Pascal Fua, wins the Koenderink Prize in 2020.

  8. As of October 2026

    Data scientist and ML engineer

    He works as a data scientist and machine learning engineer, with interests in machine learning, computer vision and software engineering.

Most-cited works

  1. BRIEF: Binary Robust Independent Elementary Features2010 · Lecture notes in computer science · 3,676 citationsWith Christoph Strecha, Pascal Fua and Vincent Lepetit
  2. BRIEF: Computing a Local Binary Descriptor Very Fast2011 · IEEE Transactions on Pattern Analysis and Machine Intelligence · 866 citationsWith Christoph Strecha, Pascal Fua and Vincent Lepetit
  3. Fast Keypoint Recognition Using Random Ferns2009 · IEEE Transactions on Pattern Analysis and Machine Intelligence · 595 citationsWith Pascal Fua and Vincent Lepetit
  4. View-based Maps2010 · The International Journal of Robotics Research · 233 citationsWith Kurt Konolige, Pascal Fua and Vincent Lepetit
  5. Keypoint Signatures for Fast Learning and Recognition2008 · Lecture notes in computer science · 71 citationsWith Pascal Fua and Vincent Lepetit

From OpenAlex, as of 21 October 2026.

  1. Google has the highest combined h-index among AI organizationsIncludes EPFL. We estimate that Google holds the highest combined h-index at 8,016, while universities account for 73% of the deduplicated total across AI organizations.
  2. The median h-index is 48 at universities and 14 at frontier AI labsIncludes EPFL. The median h-index is 48 at universities and 14 at frontier AI labs. We compare publishing careers, recent citations, dual appointments and job moves across 2,420 university researchers and 308 frontier-lab researchers.
  3. The United States employs an estimated 48% of people shaping AIIncludes EPFL. We estimate where the people shaping AI work today, how universities, companies and research institutes split across countries, and how country shares have changed since the 1960s.
  4. Universities had a net outflow of 2,068 moves in AI careersIncludes EPFL. Our estimates of career flows and median h-index across universities and companies in AI, including the role of joint appointments and earlier academic jobs.

Colleagues

People named in this biography, and people with dated positions at the same organization in the same years.

Sources and credits

Photo: We have no published photo of Michael Calonder yet. Send us a free-licensed photo.

  1. Michael Calonder - Google Scholar scholar.google.com. Checked 20 October 2026.
  2. Keypoint Signatures for Fast Learning and Recognition | ML Anthology mlanthology.org. Checked 20 October 2026.
  3. Compact Signatures for High-Speed Interest Point Description and Matching | ML Anthology mlanthology.org. Checked 20 October 2026.
  4. BRIEF: Binary Robust Independent Elementary Features | ML Anthology mlanthology.org. Checked 20 October 2026.
  5. Robust, High-Speed Interest Point Matching for Real-Time Applications - EPFL memento.epfl.ch. Checked 20 October 2026.
  6. BRIEF: Computing a Local Binary Descriptor Very Fast | Computer Vision Lab cvlab.ii.pw.edu.pl. Checked 20 October 2026.
  7. Best Paper Awards ‒ IC ‐ EPFL epfl.ch. Checked 20 October 2026.