Yehonathan Litman

I'm a third year PhD student at in the Robotics Institute, Carnegie Mellon University, advised by Shubham Tulsiani and Fernando De la Torre.

I'm focusing on how large generative models can serve as priors for faithfully reconstructing the world and capturing its underlying intrinsic properties. My work is supported in part by an NSF Graduate Research Fellowship.

Email  /  CV  /  Google Scholar  /  Twitter  /  Github

profile photo

Selected Research

MaterialFusion: Enhancing Inverse Rendering with Material Diffusion Priors
Yehonathan Litman, Or Patashnik, Kangle Deng, Aviral Agrawal, Rushikesh Zawar, Fernando De la Torre, Shubham Tulsiani
3DV, 2025
project page / arXiv / github

Distill a material diffusion prior model into material parameters during inverse rendering to improve intrinsic decomposition and novel relighting.

Global Visual‑Inertial Ground Vehicle State Estimation via Image Registration
Yehonathan Litman*, Daniel Mcgann*, Eric Dexheimer, Michael Kaess
ICRA, 2022
video / IEEEXplore

Reconstruct input images in a 3D occupancy grid and project to bird's eye view of the environment, register that to satelite imagery data to correct SLAM drift in real time without requiring GPS.

Vision‑Based Self‑Assembly for Modular Multirotor Structures
Yehonathan Litman, Neeraj Gandhi, Linh Thi Xuan Phan, David Saldaña
IEEE RA-L & ICRA, 2021   (Finalist in Multi‑Robot Systems)
video / IEEEXplore

Dynamically assign a drone agent leader to heuristically assemble a large variety of drone swarm formations using only vision and onboard sensors.

Accelerated Visual Inertial Navigation via Fragmented Structure Updates
Yehonathan Litman, Ya Wang, Ji Liu
IROS, 2019
IEEEXplore

Retain features across frames selectively based on shared information and use hardware acceleration to dramatically improve VIO SLAM efficiency.

Invariant Filter Based Preintegration for Addressing the Visual Observability Problem
Yehonathan Litman, Ya Wang, Libo Wu
IEEE MIT URTC, 2018
IEEEXplore

Addressing the visual observability problem in VIO by using invariant filtering to improve efficiency and accuracy.

Awards

  • [2022] NSF Graduate Research Fellowship Program (GRFP)
  • [2020] Stony Brook Provost’s Award for Academic Excellence (Given to 14/~5,000 graduates)
  • [2017] URECA Fellowship Grant

Misc.

manatees Save the Manatees! Even if you're not from Florida (or all the other places that have manatees), you can still help!

Credits: Jon Barron.