Animesh Karnewar
Senior Research Scientist at Qualcomm
Amsterdam, North Holland, Netherlands
Summary
👤
Senior🎓
Top SchoolAnimesh Karnewar is a Senior Research Scientist with a decade of experience advancing generative AI, particularly photo-realistic 3D generative models and on-device video generation. He holds a PhD from UCL under Niloy Mitra and Tobias Ritschel and has published influential work (HoloDiffusion, HoloFusion, GOEmbed) at top venues including CVPR, ICCV, and ECCV. He has collaborated with industry labs (Meta, Adobe) and spent time as a visiting researcher at Meta contributing to foundational 3D diffusion research before joining Qualcomm to focus on mobile-first video generation. Known for turning 2D image collections into scalable 3D generative models, he pairs deep theoretical insight with practical engineering experience from roles in autonomous driving and AI engineering. Based in Amsterdam, he blends academic rigor with product-aware research, often bridging simulation-quality visuals and real-world deployment constraints.
10 years of coding experience
5 years of employment as a software developer
HSC, Science (Electronics voc.), HSC, Science (Electronics voc.) at Fergusson CollegeBachelor's degree, Computer Engineering, 80.63%, Bachelor's degree, Computer Engineering, 80.63% at Pune Institute of Computer TechnologyUniversity College London
Stackoverflow
436reputation
63kreached
5answers
12questions
Github Skills (90)
python10
converting10
deep-learning10
self-attention10
face-generation10
text-to-image10
convolutional-neural-networks10
msg10
facenet10
face-recognition10
hyperparameter-tuning10
computer-vision10
pytorch3d10
artificial-intelligence10
tensorflow10
Programming languages (7)
Github contributions (5)
akanimax/my-deity
Oct 2017 - May 2018
I worship the one true neural network architecture that can autonomously learn everything.
Contributions:48 commits, 43 pushes, 1 branch in 7 months
neural-network
akanimax/msg-gan-v1
Aug 2018 - Apr 2020
MSG-GAN: Multi-Scale Gradients GAN (Architecture inspired from ProGAN but doesn't use layer-wise growing)
Contributions:38 commits, 2 PRs, 28 pushes in 1 year 8 months
pytorchgradientsdeep-learninggenerative-adversarial-networkmulti-scale
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.