PeopleofSuperintelligence

Researcher

Javier Romero

Also known as J. Romero

Javier Romero is a computer vision researcher whose work helps estimate human body shape and pose from images. He earned an M.Sc. from the Technical University of Madrid and a Ph.D. from the Royal Institute of Technology in Stockholm before becoming a research scientist in Max Planck's Perceiving Systems department in 2013. His work spans the SMPL body model, single-image pose fitting, detailed body scans, and Amazon's Body Labs research on extracting body information from customer photos. The SMPL Body Model Team received the 2025 PAMI Mark Everingham Prize, and Romero coauthored MHR for expressive human animation. In 2024, he is a research scientist at Meta; in 2025, he works in Meta's Codec Avatars Lab on relightable full-body avatars with face and hand detail.

Now at
Meta
Works
75
Citations
8,482
h-index
25
Badges

Publication numbers from OpenAlex, as of 22 October 2026.

Timeline

  1. 2007–2013

    Degrees and Max Planck research

    He earns an M.Sc. from the Technical University of Madrid in 2007 and a Ph.D. from the Royal Institute of Technology in Stockholm in 2011 under Danica Kragic and Hedvig Kjellström. After postdoctoral research in the Perceiving Systems department of the Max Planck Institute for Intelligent Systems in Tübingen, he becomes a research scientist there in 2013. His research focuses on human-body perception at the intersection of computer vision and graphics.

  2. 2015

    The SMPL body model

    With Matthew Loper, Naureen Mahmood, Gerard Pons-Moll, and Michael J. Black, he publishes SMPL, a learned model of human body shape and pose-dependent variation that represents a wide range of bodies in natural poses.

  3. 2016

    Fitting SMPL to one image

    In 2016, he coauthors Keep it SMPL, which estimates 3D body pose and shape from one unconstrained image by fitting SMPL to 2D joint positions.

  4. 2017–2020

    Amazon's Body Labs research

    He joins Amazon in 2017. In 2020, he is a principal applied scientist in Amazon's Body Labs unit in Barcelona, where he uses scans to extract body information from customer images.

  5. 2019

    Detailed scans from one photo

    In 2019, he coauthors FACSIMILE, a method that estimates a detailed body from one photo and recovers geometry at the image's original resolution.

  6. 2025

    A Mark Everingham Prize

    In 2025, the SMPL Body Model Team, including Romero, receives the PAMI Mark Everingham Prize at ICCV.

  7. 2025

    MHR for expressive animation

    In 2025, he coauthors MHR, a parametric human body model for expressive animation designed for integration in AR/VR and graphics pipelines.

  8. Since 2025

    Research scientist at Meta

    In 2024, he is a research scientist at Meta. In 2025, he works in Meta's Codec Avatars Lab and coauthors Relightable Full-Body Gaussian Codec Avatars, which models relightable full-body avatars with fine-grained face and hand details.

Career

  1. Since 2025MetaResearch scientist
  2. 2017–2020AmazonPrincipal Applied Scientist
  3. 2013–2019Max Planck Institute for Intelligent SystemsResearch scientist
  4. 2013–2018Max Planck Society
  5. 2013–2025University of Potsdam

Education

  1. 2011KTH Royal Institute of TechnologyPh.D.
  2. 2007Technical University of MadridM.Sc.

From the biography and OpenAlex affiliations (the years of papers that list the organization), so some years are approximate.

Most-cited works

  1. Keep It SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image2016 · Lecture notes in computer science · 1,502 citationsWith Angjoo Kanazawa
  2. A Simple Yet Effective Baseline for 3d Human Pose Estimation2017 · IEEE International Conference on Computer Vision (ICCV) · 1,466 citations
  3. Learning a model of facial shape and expression from 4D scans2017 · ACM Transactions on Graphics · 1,224 citations
  4. Embodied hands2017 · ACM Transactions on Graphics · 1,052 citations
  5. On Human Motion Prediction Using Recurrent Neural Networks2017 · IEEE Computer Society Conference on Computer Vision and Pattern Recognition · 1,015 citations

From OpenAlex, as of 21 October 2026.

  1. Google alumni have founded or led 133 other organizations, more than any other AI labIncludes Javier Romero. 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.
  2. The company share of AI researchers’ top papers was 31% in 2020–2024 and 8% in 1970–1974Includes Meta. We estimate where the people shaping AI worked when their most-cited papers appeared: the company share was 31% in 2020–2024 and 8% in 1970–1974, and Google led all organizations in 2020–2024.
  3. Companies supply the most prior-work hires at 7 of the 9 frontier AI labsIncludes Meta. Our estimates of the organizations where 550 people worked directly before joining 9 frontier AI labs across 620 career transitions, comparing the main feeder organizations per lab.
  4. Of 943 people shaping AI who worked at Google, 446 work there nowIncludes Meta. Our estimates of where the 943 people shaping AI who worked at Google and Google DeepMind work now: 446 at Google and 452 across 278 other organizations.

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 Javier Romero yet. Send us a free-licensed photo.

  1. Presenter - SIGGRAPH Asia 2024 asia.siggraph.org. Checked 21 October 2026.
  2. SMPL smpl.is.tue.mpg.de. Checked 21 October 2026.
  3. [1607.08128] Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image arxiv.org. Checked 21 October 2026.
  4. Body modeling scientist Javier Romero speaks to the value of scientific publishing amazon.science. Checked 21 October 2026.
  5. [1909.00883] FACSIMILE: Fast and Accurate Scans From an Image in Less Than a Second arxiv.org. Checked 21 October 2026.
  6. Real Virtual Humans | Real Virtual Humans | University of Tübingen virtualhumans.mpi-inf.mpg.de. Checked 21 October 2026.
  7. [2511.15586] MHR: Momentum Human Rig arxiv.org. Checked 21 October 2026.
  8. Codec Avatars Workshop @ CVPR'24 codec-avatars.github.io. Checked 21 October 2026.
  9. Presentation - SIGGRAPH 2025 Conference Schedule s2025.conference-schedule.org. Checked 21 October 2026.
  10. [2501.14726] Relightable Full-Body Gaussian Codec Avatars arxiv.org. Checked 21 October 2026.