Sanjay Bhargav


I will be joining the University of Trento as a PhD student in Information Engineering and Computer Science, where I will be working with Prof. Nicu Sebe. My research interests are broadly in 3D computer vision, geometric vision, neural rendering, generative models, and learning-based scene understanding.

I am currently a Research Fellow at the Center for Visual Information Technology (CVIT), International Institute of Information Technology Hyderabad (IIIT-H), under the supervision of Prof. C. V. Jawahar and Dr. Zakaria Laskar. My work focuses on 3D scene representation, novel-view synthesis, and neural rendering for challenging real-world driving environments.

Previously, I was a Research Intern at the Saab-NTU Joint Lab, Singapore, where I worked on 3D object detection, domain adaptation, and continual learning using LiDAR and camera sensors. I completed my five-year Integrated Master's degree in Physics from the Indian Institute of Technology Kharagpur, India.

For any inquiries, feel free to reach out to me via mail!

CV Mail Scholar Github LinkedIn

Profile picture

Publications

MV2 dataset overview
MV2: Multi-View Multi-Vehicle Driving Dataset for Novel View Synthesis
Sanjay Dharavath, Hanvitha Saraswathi Mukkamala, Faizan Farooq Khan, Ioannis Kakogeorgiou, Aditya Arun, C. V. Jawahar, Zakaria Laskar
European Conference on Computer Vision (ECCV) , 2026
Project Page / Paper / Dataset
Project image
SaViD: Spectravista Aesthetic Vision Integration for Robust and Discerning 3D Object Detection in Challenging Environments
Tanmoy Dam, Sanjay Dharavath, Sameer Alam, Nimrod Lilith, Aniruddha Maiti, Supriyo Chakraborty, Mir Feroskhan
2025 IEEE International Conference on Robotics and Automation (ICRA), 2025
Project Page / Paper /
@InProceedings{11128252, 
	author = {Tanmoy Dam and Sanjay Dharavath and Sameer Alam and Nimrod Lilith and Aniruddha Maiti and Supriyo Chakraborty and Mir Feroskhan}, 
	title = {SaViD: Spectravista Aesthetic Vision Integration for Robust and Discerning 3D Object Detection in Challenging Environments}, 
	booktitle = {2025 IEEE International Conference on Robotics and Automation (ICRA)}, 
	year = {2025}, 
}
Project image
AYDIV: Adaptable Yielding 3D Object Detection via Integrated Contextual Vision Transformer
Tanmoy Dam, Sanjay Dharavath, Sameer Alam, Nimrod Lilith, Supriyo Chakraborty, Mir Feroskhan
2024 IEEE International Conference on Robotics and Automation (ICRA), 2024
Project Page / Paper /
@InProceedings{10610908, 
	author = {Tanmoy Dam and Sanjay Dharavath and Sameer Alam and Nimrod Lilith and Supriyo Chakraborty and Mir Feroskhan}, 
	title = {AYDIV: Adaptable Yielding 3D Object Detection via Integrated Contextual Vision Transformer}, 
	booktitle = {2024 IEEE International Conference on Robotics and Automation (ICRA)}, 
	year = {2024}, 
}
Project image
Quantum Inverse Contextual Vision Transformers (Q-ICVT): A New Frontier in 3D Object Detection for AVs
Sanjay Dharavath, Tanmoy Dam, Supriyo Chakraborty, Prithwiraj Roy, Aniruddha Maiti
Proceedings of the 33rd ACM International Conference on Information and Knowledge Management, 2024
Project Page / Paper /
@InProceedings{10.1145/3627673.3679984, 
	author = {Sanjay Dharavath and Tanmoy Dam and Supriyo Chakraborty and Prithwiraj Roy and Aniruddha Maiti}, 
	title = {Quantum Inverse Contextual Vision Transformers (Q-ICVT): A New Frontier in 3D Object Detection for AVs}, 
	booktitle = {Proceedings of the 33rd ACM International Conference on Information and Knowledge Management}, 
	year = {2024}, 
}

Talks

Template

This page is based on the template of Michael Niemeyer. Checkout his GitHub repository for instructions on how to use it.