About me

I am a Ph.D. Graduate from the University of Maryland, College Park, advised by Prof. David Jacobs. My research focus is in Computer Vision and Generative AI with my dissertation titled "Leveraging Deep Generative Models for Estimation and Recognition".

I did my Masters (M.S.) in Electrical and Computer Engineering at University of Maryland, College Park. During my masters, I also had a wonderful opportunity to work with Dr. Varaprasad Bandaru as a Faculty Research Assistant in Department of Geographical Sciences at UMD. I did my undergraduate studies in Electrical Engineering at Indian Institute of Technology Delhi.

I am broadly interested in computer vision. Some of the areas I have been working on are: Leveraging deep generative models such as Latent Diffusion models for language based recognition; GANs for Domain adaptation, in particular between synthetic and real datasets; GANs; Depth, and Normal estimation; Inverse Rendering; Video classification; and Inpainting. I am looking to further explore new research areas in computer vision.

What i'm doing

  • design icon

    Computer Vision 

    Research towards state-of-the-art algorithms in computer vision. Please checkout the "Projects" tab on this page to learn more.

  • camera icon

    Astrophotography

    Photography of celestial bodies or events such as Milkyway, star trails.

    Article from my University

Resume

Education

  1. University of maryland college park

    2017 - Present

    Ph.D., Computer Vision

  2. University of maryland College park

    2015 — 2017

    M.S., Electrical and computer engineering

  3. Indian Institute of technology Delhi     

    2011 — 2015

    B.Tech., Electrical Engineering  

Experience

  1. Applied scientist intern

    Amazon GO, May, 2022 — December, 2022

    Explored the utility of various text-to-image generative models for text-based segmentation of images. Demonstrated the use of latent diffusion models (LDMs) pretrained on large-scale internet data for text-based segmentation. Proposed novel ways to utilize features from the internal stages of the LDM to improve the segmentation performance by nearly 6% on real images and 20% on AI-generated images.

  2. Research intern

    STAR Labs, May, 2020 — December, 2020

    Worked with team of researchers on various audio-visual and self-supervised learning techniques. Prototyped novel learning algorithms in large scale production system for various audio and video synthesis approaches. Integrated solutions in cross language technology stack consisting of Python, C++ and CUDA.

Link to Download Resume

Research projects

Blog

Contact

Contact Form