PeopleofSuperintelligence

Researcher

Andrew Aitken

Also known as Andrew P. Aitken

Andrew Aitken is a computer vision researcher whose papers connect medical imaging with neural image super-resolution. From 2012 to 2014, he coauthored studies on magnetic-field monitoring, diffusion-sequence artifacts, and PET reconstruction. His 2016 network enables real-time 1080p video super-resolution by extracting feature maps in low-resolution space. In 2017, he coauthored SRGAN for 4× image upscaling, a video super-resolution method using neighboring frames and motion compensation, and an initialization technique designed to prevent checkerboard artifacts. As of October 2026, he is a founding research engineer at Anam.

Now at
Anam
Works
16
Citations
22,604
h-index
12
Badges

Publication numbers from OpenAlex, as of 22 October 2026.

Timeline

  1. 2012

    Magnetic-field monitoring

    In 2012, he coauthors “Magnetic Field Monitoring of Radial Trajectories,” presented at ISMRM in Melbourne.

  2. 2013

    Correcting diffusion-sequence artifacts

    In 2013, he coauthors an ISMRM study on correcting eddy-current artifacts in unipolar and bipolar diffusion sequences for renal diffusion-tensor imaging.

  3. 2014

    PET attenuation-map artifacts

    In 2014, he coauthors an ISMRM study on how eddy-current artifacts in UTE-derived PET attenuation maps affect PET reconstruction.

  4. 2016

    Real-time video super-resolution

    In 2016, he coauthors a convolutional network for real-time super-resolution of 1080p videos, with feature maps extracted in low-resolution space.

  5. 2017

    SRGAN for 4× image upscaling

    In 2017, he coauthors SRGAN, a generative adversarial network for 4× image upscaling whose perceptual loss combines adversarial and content losses.

  6. 2017

    Spatio-temporal video super-resolution

    At CVPR 2017, he coauthors a method that uses spatio-temporal sub-pixel convolution networks and motion compensation for real-time video super-resolution.

  7. 2017

    Checkerboard-free sub-pixel initialization

    In 2017, he coauthors an initialization method for sub-pixel convolution that avoids checkerboard artifacts immediately after initialization.

  8. As of October 2026

    Founding research engineer

    As of October 2026, he is a founding research engineer at Anam.

Career

  1. NowAnamFounding Research Engineer
  2. 2017–2019Twitter
  3. 2011–2014King's College London

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

  1. The median h-index is 48 at universities and 14 at frontier AI labsIncludes King's 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. Companies supply the most prior-work hires at 7 of the 9 frontier AI labsIncludes King's College London. 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.
  3. More people shaping AI studied at Massachusetts Institute of Technology than at any other institutionIncludes King's College London. 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 King's College London. 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 Andrew Aitken yet. Send us a free-licensed photo.

  1. Abstracts mr.ethz.ch. Checked 21 October 2026.
  2. [1609.05158] Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network arxiv.org. Checked 21 October 2026.
  3. CVPR 2017 Open Access Repository openaccess.thecvf.com. Checked 21 October 2026.
  4. CVPR 2017 Open Access Repository openaccess.thecvf.com. Checked 21 October 2026.
  5. [1707.02937] Checkerboard artifact free sub-pixel convolution: A note on sub-pixel convolution, resize convolution and convolution resize arxiv.org. Checked 21 October 2026.
  6. About Anam - Building the Future of AI Avatars anam.ai. Checked 21 October 2026.