I am a Research Scientist at Apple Machine Learning Research.
I lead the research around Neural Rendering, 3D Generative models and Efficients Networks. Specifically, my work focuses on 3D generative models for humans and faces targetted towards Apple Vision Pro applications. I have also developed fast neural networks such as MobileOne and FastViT, which have shipped on several devices iPhone, iPad, Apple Vision Pro across several applications including Maps, Siri and Hand Tracking.
NeuMan is a NeRF representation of human together with the scene. From a single clip (<100 frames), NeuMan can perform view synthesis of the scene without/with the human in novel poses.
MobileOne: An Improved One millisecond Mobile Backbone
Pavan Kumar Anasosalu Vasu, James Gabriel, Jeff Zhu, Oncel Tuzel, and Anurag Ranjan
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022
