PeopleofSuperintelligence

Researcher

Rodrigo Benenson

Also known as rodrigob

Rodrigo Benenson is a computer vision researcher whose work covers pedestrian detection, street-scene datasets and large-scale image annotation. He studied electronics engineering at UTFSM and earned a robotics PhD in 2008 inside the Lara team of Mines Paristech and INRIA, with a thesis on perception for driverless vehicles. A postdoc at Visics, KU Leuven, began in 2010, and a second postdoc at the Max Planck Institute for Informatics preceded his move to Google in 2016. Along the way he coauthored the 2012 CVPR oral on pedestrian detection at 100 frames per second, the 2014 survey Ten Years of Pedestrian Detection, the 2016 Cityscapes dataset and the Open Images annotation papers of 2019 and 2022, and he was among the authors of the 2025 Gemini 2.5 report. He is a research scientist at Google.

Now at
Google
Badges

Timeline

  1. 2005–2008

    A PhD on driverless vehicles

    After studying electronics engineering at UTFSM, he starts a PhD in robotics in 2005 inside the Lara team, part of Mines Paristech and INRIA. He completes it in 2008 with a thesis on perception for driverless vehicles.

  2. 2010–2012

    Fast pedestrian detection at Visics

    In 2010 he spends his first year at Visics, KU Leuven, in a postdoc in computer vision. His CVPR 2012 oral, Pedestrian Detection at 100 Frames per Second, reaches 50 Hz in a monocular setup and 135 Hz with stixels on a street scene.

  3. 2014

    Ten years of pedestrian detection

    In 2014 he coauthors Ten Years of Pedestrian Detection, What Have We Learned? with Mohamed Omran, Jan Hosang and Bernt Schiele. The paper reviews the 40+ detectors on the Caltech benchmark and combines published strategies into a decision forest detector with the best known performance on Caltech-USA.

  4. 2016

    The Cityscapes dataset

    In 2016 he is among the authors of The Cityscapes Dataset for Semantic Urban Scene Understanding, a benchmark of stereo video sequences from 50 cities with 5000 finely annotated images and 20000 coarsely annotated ones.

  5. 2016

    A move to Google

    After a second postdoc at the Max Planck Institute for Informatics in Saarbrücken, Germany, he joins Google in 2016. He works there as a research scientist on scaling up machine scene understanding.

  6. 2019–2022

    Annotating Open Images at scale

    In 2019 he coauthors, with Stefan Popov and Vittorio Ferrari, a CVPR paper on large-scale interactive object segmentation that produces masks for 2.5M instances on the Open Images dataset. In 2022 he and Ferrari propose a pointillist way of labelling segmentation data and release 22.6M point labels over 4,171 classes on Open Images.

  7. As of October 2026

    Research scientist at Google

    He is a research scientist at Google. In July 2025 he is listed among the authors of the Gemini 2.5 report, which introduces the Gemini 2.5 Pro and Gemini 2.5 Flash models.

Career

  1. Since 2016GoogleResearch Scientist
  2. 2010–2012KU LeuvenPostdoctoral Researcher
  3. Max Planck Institute for InformaticsPostdoctoral Researcher

Education

  1. 2008MINES ParisTechPhD
  2. 2008InriaPhD
  3. Federico Santa María Technical UniversityElectronics Engineering

From the biography.

  1. Google had the most people shaping AI every year from 2014 to 2025Includes Google. Our estimates of which organizations employed the most people shaping AI each year from 1955 to 2025, tracing the shift from university labs to companies.
  2. Google has the highest combined h-index among AI organizationsIncludes Google. 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.
  3. 20% of people at companies who shape AI also hold a university role, led by Google and Stanford UniversityIncludes Google. We estimate that 539 of the 6,766 people with a known current organization (8%) hold both a university role and a company role, including 20% of people at companies and 13% of people at universities.
  4. Google alumni have founded or led 133 other organizations, more than any other AI labIncludes Google. We estimate that alumni of 17 major AI labs went on to found or lead 350 other organizations, including 226 they founded, and we trace 472 career moves directly between 23 labs since 2010.

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 Rodrigo Benenson yet. Send us a free-licensed photo.

  1. Rodrigo Benenson research.google. Checked 22 October 2026.
  2. Rodrigo Benenson github page rodrigob.github.io. Checked 22 October 2026.
  3. [1411.4304] Ten Years of Pedestrian Detection, What Have We Learned? arxiv.org. Checked 22 October 2026.
  4. [1604.01685] The Cityscapes Dataset for Semantic Urban Scene Understanding arxiv.org. Checked 22 October 2026.
  5. Rodrigo Benenson - Max Planck Institute for Informatics mpi-inf.mpg.de. Checked 22 October 2026.
  6. [2210.14142] From colouring-in to pointillism: revisiting semantic segmentation supervision arxiv.org. Checked 22 October 2026.
  7. [2507.06261] Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities arxiv.org. Checked 22 October 2026.
  8. Rodrigo Benenson - Google Scholar scholar.google.com. Checked 22 October 2026.