PeopleofSuperintelligence

Researcher

Henning Meyer

Henning Meyer is a Google Research coauthor of the Scene Representation Transformer and Kubric, two CVPR 2022 papers on novel view synthesis and synthetic training data. He came to AI from medical imaging: at Charité's Department of Radiology in Berlin, he coauthored a 2007 phantom study of softMip and other algorithms for computing thick slices from tomosynthesis mammography data. In 2012, he worked in the University of Toronto's Department of Medical Imaging, and in 2014 he coauthored a Charité paper on a phase detection algorithm for 4D cardiac CT. At Google Research, he coauthored NeSF, a 2021 method that trains 3D semantic segmentation from 2D semantic maps, and SRT, which renders new views of a scene in a single feed-forward pass. As of October 2026, he is at Google Research, with interests in radiology and deep learning.

Timeline

  1. 2007

    softMip for breast tomosynthesis

    In 2007, he coauthors a phantom study with Felix Diekmann and colleagues in the Department of Radiology at Charité-Universitätsmedizin Berlin. The study compares maximum intensity projection, an average algorithm and a new algorithm called softMip for computing thick slices from tomosynthesis mammography data.

  2. 2012

    Medical imaging in Toronto

    In 2012, he works in the Department of Medical Imaging at the University of Toronto, based at Toronto General Hospital. With Sonja Kandel and colleagues, he publishes a 2012 study comparing free breathing and breath-hold protocols for pancreatic perfusion imaging with dynamic volume CT.

  3. December 2014

    Cardiac CT software at Charité

    In December 2014, he coauthors a PLOS ONE paper with Carsten Kendziorra and Marc Dewey of Charité's Department of Radiology on a phase detection algorithm for 4D cardiac CT. Implemented in KardioPerfusion, a software framework for 4D CT myocardial perfusion analysis, the algorithm agrees with two reference readers in 97% of cases.

  4. 2021–2022

    NeSF at Google Research

    At Google Research, he coauthors NeSF, first posted in November 2021 and published in TMLR in 2022. The method recovers 3D density fields from posed RGB images and trains a 3D semantic segmentation model supervised by posed 2D semantic maps.

  5. 2021–2022

    The Scene Representation Transformer

    He is second author, after Mehdi S. M. Sajjadi, of the Scene Representation Transformer (SRT), first posted in November 2021 and presented at CVPR in June 2022. SRT processes posed or unposed RGB images of a new area, infers a set-latent scene representation and synthesizes novel views in a single feed-forward pass. It scales to interactive visualization and semantic segmentation of real-world outdoor scenes from Street View imagery.

  6. 2022

    Kubric for synthetic data

    In 2022, he is one of 34 authors of Kubric, an open-source Python framework presented at CVPR 2022. Kubric interfaces with PyBullet and Blender to generate photo-realistic scenes with rich annotations, and it scales to jobs distributed over thousands of machines.

  7. As of October 2026

    Deep learning at Google Research

    As of October 2026, he is at Google Research, with research interests in radiology and deep learning.

  1. Google had the most people shaping AI every year from 2014 to 2025Our estimates of which organizations employed the most people shaping AI from 1961 to 2025, with a year-by-year chart.
  2. The United States employs an estimated 53% of people in our data with a known employment countryOur estimates of where AI careers are concentrated now and how countries’ shares of dated positions changed over time.
  3. 46% of living people in our data with known birth and employment countries work outside their birth countryOur estimate of cross-border careers in AI, from country of birth and the country of each current organization.
  4. More people shaping AI studied at Massachusetts Institute of Technology than at any other institutionOur estimates of where the people shaping AI studied and where their careers led, from education records in cited biographies.

Sources and credits

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

  1. Thick Slices from Tomosynthesis Data Sets: Phantom Study for the Evaluation of Different Algorithms - PMC pmc.ncbi.nlm.nih.gov. Checked 19 October 2026.
  2. Comparison of free breathing versus breath-hold in perfusion imaging using dynamic volume CT - PMC pmc.ncbi.nlm.nih.gov. Checked 19 October 2026.
  3. Implementation of a Phase Detection Algorithm for Dynamic Cardiac Computed Tomography Analysis Based on Time Dependent Contrast Agent Distribution | PLOS One journals.plos.org. Checked 19 October 2026.
  4. NeSF: Neural Semantic Fields nesf3d.github.io. Checked 19 October 2026.
  5. [2111.13260] NeSF: Neural Semantic Fields for Generalizable Semantic Segmentation of 3D Scenes arxiv.org. Checked 19 October 2026.
  6. [2111.13152] Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representations arxiv.org. Checked 19 October 2026.
  7. CVPR 2022 Open Access Repository: Scene Representation Transformer openaccess.thecvf.com. Checked 19 October 2026.
  8. [2203.03570] Kubric: A scalable dataset generator arxiv.org. Checked 19 October 2026.
  9. CVPR 2022 Open Access Repository: Kubric: A Scalable Dataset Generator openaccess.thecvf.com. Checked 19 October 2026.
  10. Henning Meyer - Google Scholar scholar.google.com. Checked 19 October 2026.