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, cognition and video synthesis for drones/ aerial vehicles.

Email  /  Google Scholar  /  Twitter  /  Github

profile photo
Latest News
  • (Oct 2021) Two papers at ICCV-W 2021.
  • (Aug 2021) New paper on navigation in unstructured environments on ArXiv.
SS-SFDA SS-SFDA : Self-Supervised Source-Free Domain Adaptation for Road Segmentation in Hazardous Environments
Divya Kothandaraman, Rohan Chandra Dinesh Manocha
ICCV-W 2021
Project Page / arXiv / YouTube / GitHub / bibtex

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

GANAV GANav: Group-wise Attention Network for Classifying Navigable Regions in Unstructured Outdoor Environments
Tianrui Guan Divya Kothandaraman, Rohan Chandra Dinesh Manocha
ArXiv 2021
Project Page / arXiv / bibtex

A segmentation method for identifying safe and navigable regions in off-road terrains.

BOMUDA BoMuDA: Boundless Multi-Source Domain Adaptive Segmentation in Unconstrained Environments
Divya Kothandaraman, Rohan Chandra Dinesh Manocha
ICCV-W 2021
Project Page / arXiv / YouTube / GitHub / bibtex

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

WACV21IITM Domain Adaptive Knowledge Distillation for Driving Scene Semantic Segmentation
Divya Kothandaraman, Athira Nambiar Anurag Mittal
WACV-W 2021
Paper / YouTube / GitHub / bibtex

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

ECCVW20 Deep Atrous Guided Filter for Image Restoration in Under Display Cameras
Varun Sundar , Sumanth Hegde*, Divya Kothandaraman , Kaushik Mitra
ECCV RLQ-TOD Workshop, 2020
ArXiv / YouTube / Project Page / bibtex

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


Website template borrowed from Jon Barron.