Rawal Khirodkar

Rawal Khirodkar

Research Scientist, Meta

Email CV Scholar GitHub Twitter LinkedIn

I am a Research Scientist at Meta, passionate about making digital humans a reality.

Previously, I completed my Masters (2017-2019) and Ph.D. (2019-2023) in Robotics from Carnegie Mellon University, advised by Prof. Kris Kitani. Before that, I received my Bachelors (2013-2017) in Computer Science from IIT Bombay. My Ph.D. was supported by the Amazon Fellowship Program.

My research interests are in large-scale self-supervised learning, 3D modeling, and controllable interactive video diffusion. If you are interested in interning with me, feel free to reach out via email with your resume and research interests.

News

Nov 2025 MHR used by SAM3D-Body is out. new
Jun 2025 ATLAS accepted to ICCV 2025. new
Mar 2025 Pippo accepted to CVPR 2025.
Jan 2025 Co-organizing the 2nd Edition of Humans Workshop at CVPR 2025.
Sep 2024 Harmony4D accepted to NeurIPS 2024.
Aug 2024 Sapiens accepted to ECCV 2024 - Best Paper Candidate.
Jul 2024 URAvatar accepted to SIGGRAPH Asia 2024.
Jun 2024 EgoHumans received the EgoVis Distinguished Paper Award at CVPR 2024.
Jan 2024 Co-organizing the Humans Workshop at CVPR 2024.
Dec 2023 Ego-Exo4D accepted to CVPR 2024 - Oral Presentation.
Jul 2023 EgoHumans accepted to ICCV 2023 - Oral Presentation.
Feb 2023 OCSORT accepted to CVPR 2023.
Mar 2022 OCHMR accepted to CVPR 2022.
Jul 2021 Two papers accepted to ICCV 2021.

Experience

Bachelors, Computer Science
IIT Bombay
2013 — 2017
Masters, Robotics
Carnegie Mellon University
2017 — 2019
Ph.D., Robotics
Carnegie Mellon University
2019 — 2023
Research Intern
Amazon
2020, 2021
Research Intern
Meta
2022
Research Scientist
Meta
2023 — Present

Selected Research

MHR
Sapiens
Ego-Exo4D
URAvatar
EgoHumans

Publications

MHR: Momentum Human Rig
Ferguson et al. Mesh representation used by SAM3D-Body.
Tech Report 2025
paper github
ATLAS: Decoupling Skeletal and Shape Parameters for Expressive Parametric Human Modeling
Jinhyung Park, Javier Romero, Shunsuke Saito, Fabian Prada, Takaaki Shiratori, Yichen Xu, Federica Bogo, Shoou-I Yu, Kris Kitani, Rawal Khirodkar
ICCV 2025
project paper
Pippo: High-Res Multi-View Humans from a Single Image
Yash Kant, Ethan Weber, Jin Kyu Kim, Rawal Khirodkar, Su Zhaoen, Julieta Martinez, Igor Gilitschenski, Shunsuke Saito, Timur Bagautdinov
CVPR 2025
project paper github
Harmony4D: A Video Dataset for In-The-Wild Close Human Interactions
Rawal Khirodkar*, Jyun-Ting Song*, Jinkun Cao, Zen Luo, Kris Kitani
NeurIPS 2024, Datasets and Benchmarks Track
project paper github data
URAvatar: Universal Relightable Gaussian Codec Avatars
Junxuan Li, Chen Cao, Gabriel Schwartz, Rawal Khirodkar, Christian Richardt, Tomas Simon, Yaser Sheikh, and Shunsuke Saito
SIGGRAPH Asia 2024
project paper
Sapiens: Foundation for Human Vision Models
Rawal Khirodkar, Timur Bagautdinov, Julieta Martinez, Su Zhaoen, Austin James, Peter Selednik, Stuart Anderson, Shunsuke Saito
ECCV 2024 Oral Best Paper Candidate (Top 15)
project paper github
Real-Time Simulated Avatar from Head-Mounted Sensors
Zhengyi Luo, Jinkun Cao, Rawal Khirodkar, Alexander Winkler, Jing Huang, Kris Kitani, Weipeng Xu
CVPR 2024 Highlight
project github
Multi-Human 3D Reconstruction from In-the-Wild Videos
Committee members: Kris Kitani, Deva Ramanan, Angjoo Kanazawa, Shubham Tulsiani
Ph.D. Thesis, Carnegie Mellon University, 2023
thesis
EgoHumans: An Egocentric 3D Multi-Human Benchmark
Rawal Khirodkar, Aayush Bansal, Lingni Ma, Richard Newcombe, Minh Vo, Kris Kitani
ICCV 2023 Oral EgoVis 2023 Distinguished Paper Award
project paper github
Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Tracking
Jinkun Cao, Xinshuo Weng, Rawal Khirodkar, Jiangmiao Pang, Kris Kitani
CVPR 2023
paper github
OCHMR
Occluded Human Mesh Recovery
Rawal Khirodkar, Shashank Tripathi, Kris Kitani
CVPR 2022
project paper
Multi-Instance Pose Networks: Rethinking Top-Down Pose Estimation
Rawal Khirodkar, Visesh Chari, Amit Agrawal, Ambrish Tyagi
ICCV 2021
project paper github blog
RePOSE
RePOSE: Fast 6D Object Pose Refinement via Deep Texture Rendering
Shun Iwase, Xingyu Liu, Rawal Khirodkar, Rio Yokota, Kris M. Kitani
ICCV 2021
paper github

Media Coverage

Service

Conference ReviewerNeurIPS, ICLR, CVPR, ICCV, ECCV, SIGGRAPH, WACV, ACCV, AAAI
Journal ReviewerIJCV, TPAMI, JMLR
Workshop Organizer3D Humans at CVPR 2024 & 2025
Teaching AssistantCMU (6 Semesters), IITB (2 Semesters)

Visitors