I am currently a Computer Scientist at NASA IMPACT, where my research focuses on building and scaling AI Foundation Models for Science. I completed my MS by Research under the supervision of Dr. Amit K. Roy Chowdhury at University of California-Riverside, where my thesis explored 3D human pose estimation for the IARPA BRIAR project.
Prior this, I worked at IISc Bangalore’s Visual Computing Lab, focusing on Unsupervised Domain Adaptation and Adversarial Vulnerability in Computer Vision algorithms.
Outside of my research, I’m passionate about traveling, hiking, photography, and video editing—and I’m always up for a game of table tennis! I enjoy connecting with new people and learning their stories, so don’t hesitate to reach out. If you’d like a copy of my CV, feel free to email me at take2rohit@gmail.com
[Apr 2025] Serving as a reviewer for CVPR 2025, ICLR 2025 and ICCV 2025.
[Feb 2025] Delivered an oral presentation of my Master’s thesis STRIDE: Single-video based Temporally Continuous Occlusion-Robust 3D Pose Estimations at WACV 2025.
[Sept 2024] Our team released Prithvi WxC, a new general-purpose AI model for weather and climate. [NASA Article] [IBM Blog] [HuggingFace CEO interview]
[May 2024] Joined NASA IMPACT as a Computer Scientist II.
[Jan 2024] Started working as a Teaching Assistant for a course on Trustworthy AI by Prof. Jiachen Li.
[Nov 2023] One paper on Self-Supervised Human Silhouette Extraction under Occlusion got accepted at WACV-2024 conference [LinkedIn Post].
[July 2023] One paper on Source free Pose Adaptation got accepted at ICCV-2023 conference!
[Mar 2023] Our work at IISc on Improving Domain Adaptation through Class Aware Frequency Transformation got accepted to the International Journal of Computer Vision (IJCV).
[Oct 2022] Our paper on CoNMix for Source-free Single and Multi-target Domain Adaptation got accepted at the Winter Conference on Applications of Computer Vision (WACV) 2023.
[Apr 2022] Paper on Holistic Approach to Measure Sample-level Adversarial Vulnerability and its Utility in Building Trustworthy Systems got accepted at HCIS Workshop, CVPR’22.
Prithvi WxC - Foundation model for weather and climate. J Schmude , S Roy,...,Rohit Lal,..., . In. International Journal of Computer Vision (IJCV) [Paper] [Code]
STRIDE - Single-Video Based Temporally Continuous Occlusion-Robust 3D Pose Estimation. Rohit Lal , Saketh Bachu , Yash Garg , Arindam Dutta , Calvin-Khang Ta , Hannah D. Cruz . In. Winter Conference on Applications of Computer Vision (WACV), 2025 [Project Page] [Code] [BibTex]
Prior-guided source-free domain adaptation for human pose estimation. DS Raychaudhuri , CK Ta , A Dutta , Rohit Lal , AK Roy-Chowdhury . In. International Conference on Computer Vision (ICCV), 2023 [Paper] [Code] [BibTex]
CoNMix for Source-free Single and Multi-target Domain Adaptation. Vikash Kumar* , Rohit Lal* , Himanshu Patil , Anirban Chakraborty . In. Winter Conference on Applications of Computer Vision (WACV), 2023 [Project Page]
Holistic Approach to Measure Sample-level Adversarial Vulnerability and its Utility in Building Trustworthy Systems. Gaurav Kumar Nayak* , Ruchit Rawal* , Rohit Lal* , Himanshu Patil , Anirban Chakraborty . In. HCIS, Conference on Computer Vision and Pattern Recognition (CVPR)-2022 [Project Page]
* authors claim equal contribution
Navigation System for a Vehicle and for Navigation. Pandya Karan, Kotecha Prakrut, Iyer V Aadhithya, Gaikwad Ravishankar, Lal Rohit, Agrawal Rishesh and Shital Chiddarwar, Issued Dec 1, 2019, Patent no. 201921049473 [Patent File] [Video]
Currently working at Visual Computing Lab, Department of Computational and Data Sciences (CDS), IISc and conducting research in unsupervised learning methodologies and its applications in domain adaptation (DA) under the guidance of Dr. Anirban Chakraborty.
Collaborated with senior scientist at Centre for Artificial Intelligence & Robotics CAIR Lab, DRDO on building object detection and tracking pipeline using drone cameras which is at an altitude of 100 meters above ground. Also worked on drone imaging for pixel-wise pose-estimation and GPS coordinates extraction.
Completed my intern under Prof. Hongliang Ren at Medical Mechatronics Lab. My task was to do tracking of gaits generated by Origami robots. This task has been done using traditional CV techniques and the next step is to incorporate various deep learning techniques for 6D pose estimation.
IEEE VNIT Student Branch is a technical Society run by the students of VNIT. I head the council responsible for managing the Society and will be involved in the decision-making process of several initiatives in the tenure of the council.
IvLabs is the Robotics and Innovation Society run by the students of VNIT. I taught at various IEEE workshops related to image processing, MATLAB, basic electronics, CAD, etc to a strength of more than 100 students at every workshop which promoted technical culture.
Aaron Bobbick | Udacity