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
- July 2022: 1 paper accepted at ECCV 2022.
- June 2022: Gave a talk on synthetic data for mixed reality at CVPR 2022 workshop.
- Oct 2021: Two papers accepted at ICCV 2021.
- Sept 2021: I joined Meta Reality Labs as engineering manager leading the machine learning group.
- May 2021: Recognized as one of the top AI talent on fortune.
- April 2021: I joined AI Reverie as Head of ML, which featured in bloomberg and businesswire
- Oct 2019: 1 paper accepted at ICCV (Oral)
- May 2019: Our work Meta-Sim and Structured Domain Randomization featured in OpenAI talk and blog
- Feb. 2019: 1 paper accepted to ICRA
- Jan. 2019: Training Deep Networks with Synthetic Data recognized as breakthrough developments of 2017-2018 by MIT
- Nov. 2018: Our work Structured Domain Randomziation featured in TowardsDataScience
- Jun. 2018: Training Deep Networks with Synthetic Data picked as the top 10 coolest papers from CVPR2018 by TowardsDataScience.
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