I am a Pre-Doctoral Researcher at Google Research India. I work towards solving the problem of predicting super-resolved segmentation maps from satellite imagery in Earth Observation Science team.
Previously, I graduated from the Indian Institute of Science Bengaluru (IISc) with a M.Tech. (Research) in Computational and Data Sciences. I was part of Video Analytics Lab (VAL), where I worked towards my thesis titled Landmark Estimation and Image Synthesis Guidance using Self-Supervised Networks under the advisorship of Prof. R. Venkatesh Babu.
I have been fortunate to be part of Google Summer of Code twice to contribute to the JuliaLang . In the summer of 2019, I built Duckietown.jl, a differentiable self-driving car simulation environment that enable training of agents using differentiable programming. While in the summer of 2018, I contributed to Flux’s model zoo with Reinforcement Learning algorithms and built AlphaGo.jl to train and play zero-sum board games using Alpha(Go)Zero algorithm in JuliaLang.
My research interests lie in building Deep Learning models for generating and editing images.
CV / Google Scholar / Github / LinkedIn
News
February, 2023 : Serving as reviewer in ICCV 2023.
November, 2022 : Serving as reviewer in CVPR 2023.
October, 2022 : Attended ECCV’22 at Tel Aviv to present our works on GAN– HSR and gSR.
October, 2022 : Defended my M.Tech. (Research) thesis!
July, 2022 : Our papers on GAN regularizers (HSR and gSR) accepted at ECCV’22!
June, 2022 : Our work FLAME, which enables Few-shot Image editing using StyleGAN, got accepted in ACMMM’22!
June, 2022 : Recognized as Outstanding Reviewer at CVPR 2022!
April, 2022 : Started as Pre-Doctoral Researcher at Google Research India under the guidance of Dr. Varun Gulshan.
March, 2022 : Gave colloquium and submitted thesis on Landmark Estimation and Image Synthesis Guidance using Self-Supervised Networks at IISc.
tejank10@gmail.com
Google Research India
Bengaluru, KA