About Me

Hello!

I am a PostDoc researcher in Perceiving Systems at the MPI for Intelligent Systems, where I completed my Ph.D. under the guidance of Professor Michael J. Black and Dr. Dimitrios Tzionas. My research focuses on generating Virtual Humans that move and interact with 3D scenes and objects like Real Humans.

My research interests are broad and include precise motion capture (MoCap) using multimodal sensors (IMUs, Cameras, Pressure Sensors, etc.), 3D reconstruction from images, Human-Scene Interaction, and 3D representation. Recently, I’ve expanded my interests to include cutting-edge topics in AI such as diffusion models and Large Language Models (LLMs) for object interaction.

Feel free to contact me about my research, collaborations, or anything else here.

Interests
  • Virtual Avatar Animation
  • Human-Object Interaction
  • Grasp Prediction
  • Motion Synthesis and Tracking
  • Object-Interaction Detection
  • 3D Geometry Representation
  • Diffusion Models
  • Large Language Models (LLMs)
Education

  • PostDoc Researcher - AI and Computer Vision, 2024-Present

    Max Planck Institute for Intelligent Systems, Tuebingen, DE.

  • Ph.D. in Computer Science - AI and Computer Vision, 2018–2024

    Max Planck Institute for Intelligent Systems, Tuebingen, DE.

  • M.Sc. in Mechanical Engineering - Applied Mechanics (Control and Robotics), 2014-2017

    Sharif University of Technology, Tehran, IR.

  • B.Sc. in Mechanical Engineering - Mechatronics, 2010-2014

    Isfahan University of Technology, Isfahan, IR.

Recent News

PhD Defense Completed - check the photo gallery!
I have successfully defended my PhD thesis on July 4th, 2024. It was an incredible journey, and I am grateful for the support and guidance from my advisors, committee members, and colleagues.
Jul 4, 2024

Open Positions

We are always looking for for passionate and dedicated interns to join our research group.

Jul 15, 2024
Internship Opportunity in Our Research Group

We are currently seeking passionate and dedicated interns to join our esteemed research group. This is a unique opportunity to work on pioneering research projects and gain invaluable experience in cutting-edge technologies.

Publications

For a complete and up-to-date list of publications, check out my Google Scholar.

Quickly discover relevant content by filtering publications.
HUMOS: Human Motion Model Conditioned on Body Shape
Abstract Generating realistic human motion is crucial for many computer vision and graphics applications. The rich diversity of human body shapes and sizes significantly influences how people move. However, existing motion models typically overlook these differences, using a normalized, average body instead.
Shashank Tripathi, Omid Taheri, Christoph Lassner, Michael Black, Daniel Holden, Carsten Stoll
Cite PDF arXiv Video Code ECCV2024
HUMOS: Human Motion Model Conditioned on Body Shape
WANDR: Intention-guided Human Motion Generation
Abstract Synthesizing natural human motions that enable a 3D human avatar to walk and reach for arbitrary goals in 3D space remains an unsolved problem with many applications. Existing methods (data-driven or using reinforcement learning) are limited in terms of generalization and motion naturalness.
Markos Diomataris, Nikos Athanasiou, Omid Taheri, Xi Wang, Otmar Hilliges, Michael J. Black
Cite PDF arXiv Video Code Project CVPR2024
WANDR: Intention-guided Human Motion Generation
GRIP: Generating Interaction Poses Using Spatial Cues and Latent Consistency
Abstract Hands are dexterous and highly versatile manipulators that are central to how humans interact with objects and their environment. Consequently, modeling realistic hand-object interactions, including the subtle motion of individual fingers, is critical for applications in computer graphics, computer vision, and mixed reality.
Omid Taheri, Yi Zhou, Dimitrios Tzionas, Yang Zhou, Duygu Ceylan, Soren Pirk, Michael J. Black
Cite PDF arXiv Video Code Poster Project 3DV2024
GRIP: Generating Interaction Poses Using Spatial Cues and Latent Consistency
InterCap: Joint Markerless 3D Tracking of Humans and Objects in Interaction
Abstract Humans constantly interact with objects to accomplish tasks. To understand such interactions, computers need to reconstruct these in 3D from images of whole bodies manipulating objects, e.g., for grasping, moving, and using the latter.
Yinghao Huang, Omid Taheri, Michael J. Black, Dimitrios Tzionas
Cite PDF Paper Video Code Data Project IJCV2024
InterCap: Joint Markerless 3D Tracking of Humans and Objects in Interaction
ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulation
Abstract Humans intuitively understand that inanimate objects do not move by themselves, but that state changes are typically caused by human manipulation (e.g., the opening of a book). This is not yet the case for machines.
Zicong Fan, Omid Taheri, Dimitrios Tzionas, Muhammed Kocabas, Manuel Kaufmann, Michael J. Black, Otmar Hilliges
Cite PDF arXiv Video Code/Competition Data Project CVPR2023
ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulation
See all publications

Skills

Python

Experienced in Python programming.

C/C++

Proficient in C and C++ programming.

PyTorch & TensorFlow

Skilled in PyTorch and TensorFlow.

Git

Version control using Git.

LLMs

Expertise in Large Language Models.

GenAI

3D Generation

Transformers

Proficient in using Transformer models.

Diffusion Models

Experienced with Diffusion Models.

Computer Vision

Expertise in Computer Vision.

Human-Object Interaction

Experienced in Human-Object Interaction.

Motion Capture

Experienced in Motion Capture techniques.

IMU Sensors

Experienced with IMU Sensors.

3D Representations

Expertise in 3D Representation.

3D Avatar Motion Synthesis

Research Experience

 
 
 
 
 
Postdoctoral Researcher
Max Planck Institute for Intelligent Systems
Jan 2024 – Present Tuebingen, DE
 
 
 
 
 
Ph.D. Researcher
Max Planck Institute for Intelligent Systems
Jan 2018 – Dec 2023 Tuebingen, DE
 
 
 
 
 
PhD Research Intern
Adobe Inc.
Jun 2022 – Nov 2022 Remote, San Jose
 
 
 
 
 
Motion Capture
Max Planck Institute for Intelligent Systems
Jan 2018 – Present Tuebingen, DE

Collecting motion data with various systems including:

  • Vicon MoCap System
  • 3D Scanners
  • RGB Cameras
  • IMU Sensors
  • Pressure Sensors
  • Gaze Tracker
 
 
 
 
 
Motion Analysis Researcher
Movafaghian Research Center
Jan 2016 – Jan 2017 Tehran, IR
Capturing and analyzing human motion data using IMU sensors and RGB cameras.

Awards & Honors

Finalist for Meta PhD Fellowship
Meta Inc. Jan 2023
Winner of the AWS reading group competition
ICVSS Summer School Jan 2022
Admitted to IMPRS-IS Program
MPI for Intelligent Systems Jan 2021
Ph.D. Fellowship
Max Planck Institute for Intelligent Systems Jan 2018
Ph.D. Fellowship (Declined)
Sharif University of Technology Jan 2018
Member of Iran’s National Elites Foundation
Iran’s National Elites Foundation Jan 2014 – Dec 2018
Honorary M.Sc. Admission
Sharif University of Technology Jan 2014
Ranked 4th & 6th in National Olympiad of Mech. Eng.
Jan 2013
Recognized as Exceptionally-Talented Student
Jan 2010 – Dec 2017
Ranked 1st in Mechanical Engineering Department in B.Sc.
Isfahan University of Technology Jan 2010
Among Top 0.5% in National University Entrance Exam
Jan 2010

Contact

Access Map