I lead the machine learning team within the synthetic data organization at Reality Labs, Meta. My group works on problems at the juncture of machine learning, computer vision and computer graphics. We tackle challenges in domain adaptation, neural rendering and other sim2real problems for mixed reality. Before joining Meta, I was the head of machine learning at synthetic data startup, AI Reverie. Prior to this, I worked at Nvidia where I spent 6 years on synthetic data research in computer vision. While at Nvidia, my group delivered some of the prominent works in synthetic data creation. I graduated with a B.Tech in E&ECE from Indian Institute of Technology (IIT) Kharagpur, India, in 2010, and MASc in Computer Engineering from University of Waterloo, Canada, in 2013.

News

Publications

Self-Supervised Object Detection via Generative Image Synthesis
Siva Karthik M, Shalini De Mello, Aayush Prakash, Umar Iqbal, Sifei Liu, Thu Nguyen-Phuoc, Carsten Rother, Jan Kautz
In International Conference of Computer Vision (ICCV) 2021

Self-Supervised Real-to-Sim Scene Generation
Aayush Prakash, Shoubhik Debnath, Jean-Francois Lafleche, Eric Cameracci, Gavriel State, Stan Birchfield, Marc T. Law
In International Conference of Computer Vision (ICCV) 2021

Meta-Sim: Learning to Generate Synthetic Datasets
Amlan Kar, Aayush Prakash, Ming-Yu Liu, Eric Cameracci, Justin Yuan, Matt Rusiniak, David Acuna, Antonio Torralba, Sanja Fidler
In International Conference of Computer Vision (ICCV) 2019 (Oral)

Structured Domain Randomization: Bridging the Reality Gap by Context-Aware Synthetic Data
Aayush Prakash, Shaad Boochoon, Mark Brophy, David Acuna, Eric Cameracci, Gavriel State, Omer Shapira, Stan Birchfield
In International Conference on Robotics and Automation (ICRA) 2019

Training Deep Networks with Synthetic Data: Bridging the Reality Gap by Domain Randomization
Aayush Prakash, Jonathan Tremblay , David Acuna, Mark Brophy, Varun Jampani, Cem Anil, Thang To, Eric Cameracci, Shaad Boochoon, Stan Birchfield
In Computer Vision and Pattern Recognition Autonomus Driving Workshop (CVPR) 2018

An instruction scratchpad memory allocation for the precision timed architecture
Aayush Prakash, Hiren D Patel
IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 2013

Parallel simulation of mixed-abstraction SystemC models on GPUs and multicore CPUs
Rohit Sinha, Aayush Prakash, Hiren D Patel
In 17th Asia and South Pacific Design Automation Conference 2012

Patents

Scene graph generation for unlabeled data
Aayush Prakash, Shoubhik Debnath, Jean-Francois Lafleche, Eric Cameracci, Marc T. Law
US Patent App. 17/226,561

Learning to Generate Synthetic Datasets for Training Neural Networks
Amlan Kar, Aayush Prakash, Ming-yu Liu, David Jesus Acuna Marrero, Antonio Torralba Barriuso, Sanja Fidler
US Patent App. 16/685,795

Generation of Synthetic Images For Training a Neural Network Model
Jonathan Tremblay, Aayush Prakash, Mark A Brophy, Varun Jampani, Cem Anil, Stanley Thomas Birchfield, Thang Hong To, David Jesus Acuna Marrero
US Patent 11,182,649