Profile Picture

Mosam Dabhi

I am a 2nd-year M.S. in Robotics student in the Robotics Institute at Carnegie Mellon University , working with Prof. Simon Lucey on computer vision & artificial intelligence research at CI2CV Computer Vision Lab . Prior to joining M.S., I worked as Research Associate with Prof. Nathan Michael at RISLab . I received my B.Tech. in Electronics and Communicaton Engineering from National Institute of Technology, Surat .

I am interested in solving 3D reconstruction problems using self-supervised learning techniques. The lasting impact of 3D scene understanding research will not be confined within the expensive labs of industry and academia — it will be democratized within the hands of human consumers and intelligent robots operating in the real world. I view research through a long-term lens which allows me to focus on designing algorithms with real-world transferability in mind. In the long term, my research goal is to automate geometric factorization and reconstruction of the 3D world from image/video data, in turn to improve data and learning efficiency in visual recognition systems.

I have been fortunate to collaborate during my internship with Ian Fasel and Joshua Susskind at Apple Inc.

Research Interests: Computer Vision, Machine Learning, Robotics
Contact: mosam[at]cmu.edu

Publications

High Fidelity 3D Reconstructions with Limited Physical Views
Mosam Dabhi, Chaoyang Wang, Kunal Saluja, Laszlo Jeni, Ian Fasel, Simon Lucey

3DV 2021 [ PDF, Code, Video, Project Webpage ]


Real-Time Information-Theoretic Exploration with Gaussian Mixture Model Maps
Wennie Tabib, Kshitij Goel, John Yao, Mosam Dabhi, Curtis Boirum, Nathan Michael

RSS 2019 [ PDF, Video ]


Fast and Agile Vision-Based Flight with Teleoperation and Collision Avoidance on a Multirotor
Alex Spitzer, Xuning Yang, John Yao, Aditya Dhawale, Kshitij Goel, Mosam Dabhi, Matt Collins, Curtis Boirum, Nathan Michael

ISER 2018 [ PDF, Video ]


Aggressive Flight Performance using Robust Experience-driven Predictive Control Strategies: Experimentation and Analysis
Mosam Dabhi, Alex Spitzer, Nathan Michael

Robotics Institute Repository [ PDF, Video ]


Planning Aggressive, Dynamically Feasible and Optimal Trajectories for Autonomous Vehicles in Cluttered Environments using Mixed Integer Programming
Mosam Dabhi, Vishnu Desaraju, Nathan Michael

Robotics Institute Summer Scholars Poster Presentation 2016 [ Poster, Video ]


Implementation of Experience-driven Predictive Control on Computationally Constrained Platform
Mosam Dabhi, Nathan Michael

Robotics Institute Summer Scholars Poster Presentation 2017 [ Poster ]


Last modified by Mosam Dabhi, 1-1-2021.