Aamir Mustafa

Reseach Scientist at Yoti

Cambridge, England, United Kingdom
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts

Summary

👤
Senior
🎓
Top School
Aamir Mustafa is a research scientist and PhD candidate at the University of Cambridge with eight years of experience in computer vision, deep learning, and image/video processing. He combines strong academic output—papers at ECCV, ICCV, TPAMI and TIP—with industry impact, delivering a real-time 4K tone-mapping model that is 15× faster and 100× smaller than prior work. His research spans practical image restoration and perceptual loss design, including a distortion-specific loss that outperforms VGG/LPIPS even when trained on a single natural image. At Yoti he applies these advances to production problems while his Cambridge projects focus on interpretable latent representations for cinematic color grading and data-efficient image-to-image translation. He has a track record of turning cutting-edge research into lightweight, deployable models and defenses against adversarial attacks. Based in Cambridge, UK, he blends deep theoretical insight with pragmatic engineering to push visual AI toward real-world scalability.
code8 years of coding experience
bookDoctor of Philosophy - PhD, Computer Graphics & Vision, Doctor of Philosophy - PhD, Computer Graphics & Vision at University of Cambridge
bookBachelor of Technology (B.Tech.), Electronics and Communications Engineering, Bachelor of Technology (B.Tech.), Electronics and Communications Engineering at National Institute of Technology Srinagar
github-logo-circle

Github Skills (8)

discriminator10
super-resolution9
adversarial-attacks8
image-translation6
deep-neural-networks4
pytorch1
machine-learning1
deep-learning1

Programming languages (3)

HTMLJupyter NotebookPython

Github contributions (5)

github-logo-circle
gfxdisp/mdf

Apr 2021 - Sep 2022

Multi-scale discriminator feature-wise loss function
Contributions:7 commits, 6 pushes, 12 comments in 1 year 5 months
discriminator
Transformation Consistency Regularization- A Semi-Supervised Paradigm for Image-to-Image Translation
Contributions:10 commits, 21 pushes, 1 branch in 2 years 1 month
image-translation
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.
Request Free Trial