Divya Kothandaraman

I am a Computer Science PhD student at the University of Maryland College Park, working with Dr. Dinesh Manocha at the GAMMA Lab. Previously, I was an undergraduate (five year dual degree) at the Indian Institute of Technology Madras, where I obtained a bachelors degree in Electrical Engineering, and masters degree in Data Sciences.

My current research is in computer vision and deep learning, with a special focus towards perception and video synthesis for aerial scenes.

Email  /  Google Scholar  /  Twitter  /  Github

• (Mar 2023) Aerial Diffusion is on ArXiv !.
• (Jan 2023) One paper accepted to ICRA 2023.
• (Oct 2022) Two papers have been accepted to WACV 2023.
• (Sep 2022) Differentiable FAR is on ArXiv.
• (July 2022) FAR: Fourier Aerial Video Recognition has been accepted to ECCV 2022.

A text-guided image to image diffusion model to generate aerial views from a single ground-view image.

A differentiable feature disentanglement method to learn "static salient" and "dynamic salient" regions for aerial video action recognition.

A generic source-free active domain adaptation method that can handle shifts in output label space.

An efficient aerial video action recognition method, with novel frequency domain techniques, vis-a-vis, Fourier object disentanglement and Fourier attention.

An attention-based segmentation method for identifying safe and navigable regions in off-road terrains.

A self-supervised learning approach for source free unsupervised road segmentation in adverse weather environments and low light conditions.

A multi-source boundless unsupervised domain adaptation algorithm for semantic segmentation in unstructured environments.

An approach for domain adaptive semantic segmentation in models with limited memory.

Guided Filters when incorporated in a deep network can efficiently recover severely degraded, mega-pixel resolution images.