4D Reconstruction From Monocular Video

Authors: Manan Shah. Project Advisors: Yehonathan Litman, Xiaoxuan Ma, Nicolas Ugrinovic, Kris Kitani, Fernando De La Torre, Shubham Tulsiani
Team
Manan Shah

Manan is a Master of Science in Computer Vision student at Carnegie Mellon University, expected to graduate in December 2026. He is working on 4D reconstruction from monocular videos at CMU. He will be interning as a machine learning engineer with the Firefly Foundry team at Adobe for the summer of 2026. His research interests lie in 3D/4D vision, generative models, and vision-language models (VLMs). Previously, he worked at streamingo.ai on human activity recognition with VLMs and at the Vision and AI Lab, IISc, on generative models. He graduated with a Bachelor’s in Computer Science from the Indian Institute of Technology, Mandi.
Yehonathan Litman

Xiaoxuan (Shirley) Ma

Nicolas Ugrinovic

Kris Kitani

Fernando De La Torre

Shubham Tulsiani
