Bio

I am a PhD student at the Robotics Institute, Carnegie Mellon University (CMU) working with Simon Lucey, and Laszlo Jeni at CI2CV Computer Vision Lab and Computational Behavior Lab. Previously, I finished my Masters at CMU under the guidance of Simon Lucey. Before that, I worked as a Research Assistant with Nathan Michael at Resilient Intelligent Systems Lab (RISLab).

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.

News

Oct. 2021
Our paper "High Fidelity 3D Reconstructions with Limited Physical Views" is accepted at 3DV 2021! Watch my 2 min. talk and 10 min. talks here.
Aug. 2021
I have accepted the offer to pursue Ph.D. at the Robotics Institute, Carnegie Mellon University.
June 2021
I will rejoin Ian Fasel's group at the Apple Inc., San Francisco over the summer and continue working on deep learning for 3D reconstruction.
May 2021
I just graduated with Masters at CMU with my thesis on Multi-view NRSfM: Affordable Setup for High-Fidelity 3D Reconstruction. There's a few interesting thoughts in there - especially check out the introduction and conclusion!

Publications

High Fidelity 3D Reconstructions with Limited Physical Views
3DV 2021
Mosam Dabhi, Chaoyang Wang, Kunal Saluja, Laszlo Jeni, Ian Fasel, Simon Lucey
Real-Time Information-Theoretic Exploration with Gaussian Mixture Model Maps
RSS 2019
Wennie Tabib, Kshitij Goel, John Yao, Mosam Dabhi, Curtis Boirum, Nathan Michael
Fast and Agile Vision-Based Flight with Teleoperation and Collision Avoidance on a Multirotor
ISER 2018
Alex Spitzer, Xuning Yang, John Yao, Aditya Dhawale, Kshitij Goel, Mosam Dabhi, Matt Collins, Curtis Boirum, Nathan Michael
Aggressive Flight Performance using Robust Experience-driven Predictive Control Strategies: Experimentation and Analysis
Technical Report, Robotics Institute Repository
Mosam Dabhi, Alex Spitzer, Nathan Michael
Planning Aggressive, Dynamically Feasible and Optimal Trajectories for Autonomous Vehicles in Cluttered Environments using Mixed Integer Programming
Robotics Institute Summer Scholars Poster Presentation 2016
Mosam Dabhi, Vishnu Desaraju, Nathan Michael
Implementation of Experience-driven Predictive Control on Computationally Constrained Platform
Robotics Institute Summer Scholars Poster Presentation 2017
Mosam Dabhi, Nathan Michael