PeopleofSuperintelligence

Researcher

Fernando De la Torre

Also known as Fernando De la Torre Frade

Fernando De la Torre is a computer vision and machine learning researcher whose work analyzes faces and human behavior from multimodal data. He earned engineering degrees in Barcelona and joined Carnegie Mellon University's Robotics Institute as research faculty in 2005. He helped develop IntraFace for facial feature tracking and expression analysis, then founded FacioMetrics, a facial image analysis company acquired by Facebook in 2016. After his Facebook/Meta work on mobile augmented reality, he returned to CMU in May 2021. As of October 2026, he is a research professor at CMU and directs the Human Sensing Laboratory; his work includes 3D avatars and immersive sports viewing.

Badges

Timeline

  1. 1994–2002

    Engineering degrees in Barcelona

    He earns a B.Sc. in telecommunications in 1994, an M.Sc. in electronic engineering in 1996, and a Ph.D. in electronic engineering in 2002 at La Salle School of Engineering, Ramon Llull University, in Barcelona.

  2. Since 2005

    Research at Carnegie Mellon

    He joins Carnegie Mellon University's Robotics Institute as research faculty in 2005. His research uses machine learning, signal processing and computer vision to understand human behavior through multimodal sensors.

  3. 2014

    Supervised Descent Method

    With Xuehan Xiong, he posts the Supervised Descent Method on arXiv in 2014. The method learns descent maps from examples to solve nonlinear least-squares problems, including facial feature detection and 3D pose estimation.

  4. 2014–2016

    Founding FacioMetrics

    He founds FacioMetrics in 2014 to license technology for facial image analysis. The CMU spin-off works on face recognition, facial feature tracking, facial expression analysis, facial attributes and gaze tracking; Facebook acquires it in November 2016.

  5. December 2015–February 2016

    IntraFace facial analysis software

    In December 2015, he and colleagues develop IntraFace, which CMU announces will be available to researchers in February 2016. The software uses machine learning to track facial features, then personalizes its face model for expression analysis.

  6. May 2021

    Computer vision for AR

    He returns full-time to CMU's Robotics Institute in May 2021 after Facebook/Meta service. At Facebook/Meta, his team develops computer-vision techniques for mobile augmented reality effects, including face tracking, hand detection, hair coloring and background removal.

  7. March 2026

    SuperHead 3D avatars

    He coauthors SuperHead, a framework that creates animatable 3D head avatars from low-quality visual inputs. The method uses multi-view depth and expression supervision to preserve geometry and identity as an avatar moves and speaks.

  8. As of October 2026

    Research Professor at CMU

    He is a research professor at Carnegie Mellon University's Robotics Institute and directs the Human Sensing Laboratory. His work in 3D immersive viewing lets sports viewers enter a game and watch from any angle.

Career

  1. Since 2005Carnegie Mellon UniversityResearch Faculty, Research Professor
  2. Until 2021Meta
  3. 2014–2016FacioMetricsFounder

Education

  1. 2002Ramon Llull UniversityB.Sc., M.Sc., Ph.D.

From the biography.

  1. 11% of AI doctorate holders from 2010 to 2016 founded or led a company or lab by 10 years after graduationIncludes Fernando De la Torre. We estimate how often AI doctorate holders founded or led a company or lab by 10 years after graduation, how waiting times compare between founders and top jobs, and which universities trained the most.
  2. 16% of AI career moves in the 2020s went from a university to a companyIncludes Fernando De la Torre. We estimate that 16% of AI career moves in the 2020s went from a university to a company; 29% of moves starting at a university went to a company, and 76% ended the university role.
  3. More people shaping AI studied at Massachusetts Institute of Technology than at any other institutionIncludes Carnegie Mellon University. We estimate where the people shaping AI studied and where their careers led. Massachusetts Institute of Technology leads with 467 former students, including 291 recorded doctorates.
  4. The company share of AI researchers’ top papers was 31% in 2020–2024 and 8% in 1970–1974Includes Carnegie Mellon University. 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.

Colleagues

People with dated positions at the same organization in the same years.

Sources and credits

Photo: We have no published photo of Fernando De la Torre yet. Send us a free-licensed photo.

  1. Fernando De la Torre cs.cmu.edu. Checked 21 October 2026.
  2. Fernando De la Torre Frade - The Robotics Institute - CMU ri.cmu.edu. Checked 21 October 2026.
  3. Supervised Descent Method for Solving Nonlinear Least Squares Problems in Computer Vision arxiv.org. Checked 21 October 2026.
  4. NSF I-Corps Site Teams Spring 2015 cmu.edu. Checked 21 October 2026.
  5. Facebook acquires facial image analysis startup FacioMetrics - Computerworld computerworld.com. Checked 21 October 2026.
  6. CMU Makes Facial Image Analysis Software Available to Researchers cmu.edu. Checked 21 October 2026.
  7. SuperHead: Improving Realism in Animatable 3D Head Avatars cmu.edu. Checked 21 October 2026.
  8. Fernando De la Torre cmu.edu. Checked 21 October 2026.
  9. Carnegie Mellon Experts on Entrepreneurship, AI and Innovation cmu.edu. Checked 21 October 2026.