PeopleofSuperintelligence

Researcher

Johannes Totz

Johannes Totz is a computer vision researcher and robotics co-founder whose work spans surgical image guidance, neural-network super-resolution, and video frame interpolation. He completed a doctorate in the Department of Computing at Imperial College London in November 2012 and coauthored research on laparoscopic liver surgery registration at University College London's Centre for Medical Image Computing in June 2015. With a Twitter affiliation, he coauthored the efficient sub-pixel convolutional network at CVPR in 2016 and the SRGAN paper presented at CVPR in July 2017, contributed to spatio-temporal video super-resolution and the FIGAN frame interpolation network in 2017, and was granted US patents on frame interpolation and visual processing in 2021 and 2022. In 2024, he co-founded Paddington Robotics alongside Zehan Wang and Yuntian Fang, where he is chief technology officer.

Badges

Timeline

  1. November 2012

    PhD at Imperial College London

    In November 2012, he completes his PhD in the Department of Computing at Imperial College London with the thesis "Appearance Modelling and Reconstruction for Navigation in Minimally Invasive Surgery".

  2. 2015

    Surgical image guidance at UCL

    At University College London, where he serves on the research staff of the Department of Computer Science, he coauthors "Locally rigid, vessel-based registration for laparoscopic liver surgery" in June 2015 from the Centre for Medical Image Computing. The paper presents a laparoscopic ultrasound image guidance system and studies locally rigid registration for laparoscopic liver surgery.

  3. 2016

    Efficient sub-pixel convolutional network

    With a Twitter affiliation and a twitter.com email address, he coauthors the CVPR 2016 paper "Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network" alongside Wenzhe Shi, Zehan Wang, Daniel Rueckert and others. An efficient sub-pixel convolution layer in the model learns an array of upscaling filters, producing the first convolutional neural network capable of real-time super-resolution of 1080p video on a single K2 GPU.

  4. 2016–2017

    The SRGAN super-resolution paper

    Affiliated with Twitter, he is one of eleven authors of "Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network", posted to arXiv in September 2016 and presented at CVPR in July 2017. SRGAN is a generative adversarial network for image super-resolution and the first framework capable of inferring photo-realistic natural images for 4x upscaling factors.

  5. July 2017

    Spatio-temporal video super-resolution

    At CVPR in July 2017, Totz coauthors "Real-Time Video Super-Resolution With Spatio-Temporal Networks and Motion Compensation". The work introduces spatio-temporal sub-pixel convolution networks that exploit temporal redundancies across video frames to improve reconstruction accuracy at real-time speed.

  6. November 2017

    Frame interpolation with FIGAN

    In November 2017, he coauthors "Frame Interpolation with Multi-Scale Deep Loss Functions and Generative Adversarial Networks" on arXiv. This work presents FIGAN, a multi-scale generative adversarial network for video frame interpolation.

  7. 2021–2022

    Patents on visual processing

    In September 2021, he is granted patent US11122238B1 for "Frame interpolation with multi-scale deep loss functions and generative adversarial networks" alongside co-inventors Joost van Amersfoort, Wenzhe Shi, Jose Caballero, Alfredo Alejandro Acosta Diaz, Francisco Massa and Zehan Wang. In December 2022, he is granted patent US11528492B2 for "Machine learning for visual processing".

  8. Since 2024

    Co-founding Paddington Robotics

    Totz co-founds Paddington Robotics with Zehan Wang and Yuntian Fang in 2024. The company raises £1.9 million in 2025 with backing from 7percent Ventures, and in April 2026 he serves as its co-founder and chief technology officer.

Career

  1. 2016–2017Twitter
  2. University College LondonResearch Staff

Education

  1. 2012Imperial College LondonPhD

From the biography.

  1. The median h-index is 48 at universities and 14 at frontier AI labsIncludes University College London. 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.
  2. 20% of people at companies who shape AI also hold a university role, led by Google and Stanford UniversityIncludes University College London. 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.
  3. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other universityIncludes University College London. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other university. We compare doctorate and 5+ year employment links, career timing and current workplaces for 187 major-prize and 1,111 best-paper winners.
  4. Of 943 people shaping AI who worked at Google, 446 work there nowIncludes University College London. 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 Johannes Totz yet. Send us a free-licensed photo.

  1. Appearance Modelling and Reconstruction for Navigation in Minimally Invasive Surgery spiral.imperial.ac.uk. Checked 22 October 2026.
  2. Locally rigid, vessel-based registration for laparoscopic liver surgery - PMC ncbi.nlm.nih.gov. Checked 22 October 2026.
  3. Johannes Totz - UCL Department of Computer Science www0.cs.ucl.ac.uk. Checked 22 October 2026.
  4. Locally rigid, vessel-based registration for laparoscopic liver surgery - King's College London kclpure.kcl.ac.uk. Checked 22 October 2026.
  5. CVPR 2016 Open Access Repository openaccess.thecvf.com. Checked 22 October 2026.
  6. [1609.05158] Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network arxiv.org. Checked 22 October 2026.
  7. [1609.05158] Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network (ar5iv) ar5iv.labs.arxiv.org. Checked 22 October 2026.
  8. [1609.04802] Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arxiv.org. Checked 22 October 2026.
  9. CVPR 2017 Open Access Repository openaccess.thecvf.com. Checked 22 October 2026.
  10. [1609.04802] Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network (ar5iv) ar5iv.labs.arxiv.org. Checked 22 October 2026.
  11. CVPR 2017 Open Access Repository openaccess.thecvf.com. Checked 22 October 2026.
  12. [1711.06045] Frame Interpolation with Multi-Scale Deep Loss Functions and Generative Adversarial Networks arxiv.org. Checked 22 October 2026.
  13. US11122238B1 - Frame interpolation with multi-scale deep loss functions and generative adversarial networks - Google Patents patents.google.com. Checked 22 October 2026.
  14. US11528492B2 - Machine learning for visual processing - Google Patents patents.google.com. Checked 22 October 2026.
  15. Zehan Wang | Bae HQ thebaehq.com. Checked 22 October 2026.
  16. AI Research Scientist (£120k-£200k + Equity) at Paddington Robotics Limited at Paddington Robotics Limited | Standout | Standout standout.work. Checked 22 October 2026.