EgoControl: Controllable Egocentric Video Generation via 3D Full-Body Poses
*Enrico Pallotta, *Sina Mokhtarzadeh Azar, Lars Doorenbos, Serdar Ozsoy, Umar Iqbal, Juergen Gall
Sina Mokhtarzadeh Azar
I'm a PhD student in the Computer Vision Group at the University of Bonn working on Controllable Video Generation under the supervision of Prof. Dr. Jürgen Gall. Previously, I was a Research Assistant in the Computer Vision Lab at the University of Würzburg, where I worked with Prof. Dr. Radu Timofte .
I got my Master's degree in Artificial Intelligence from Amirkabir University of Technology where I worked on Group Activity Recognition under the supervision of Dr. Ahmad Nickabadi. I did my Bachelor's in Computer Engineering at the same university.
News
- 2026 JuneStarted my internship at Microsoft Research Cambridge to work on Audio-Visual World Models.
- 2026 FebruaryEgoControl got accepted to CVPR 2026.
- 2025 SeptemberWe won the JUPITER supercomputer grant award for the HoMe project (750k H100 gpu hours)
Research
I'm generally interested in Video Generation and Understanding. Recently, my research is focused mostly on investigating various ways of Controlling Video Generation models.
Sequence-Adaptive Video Prediction in Continuous Streams using Diffusion Noise Optimization
Sina Mokhtarzadeh Azar, Emad Bahrami, Enrico Pallotta, Gianpiero Francesca, Radu Timofte, Juergen Gall
CamC2V: Context-aware Controllable Video Generation
Luis Denninger, Sina Mokhtarzadeh Azar, Juergen Gall
SyncVP: Joint Diffusion for Synchronous Multi-Modal Video Prediction
Enrico Pallotta, Sina Mokhtarzadeh Azar, Shuai Li, Olga Zatsarynna, Juergen Gall
Speeding Up Online Self-Supervised Learning by Exploiting Its Limitations
Sina Mokhtarzadeh Azar, Radu Timofte
Convolutional Relational Machine for Group Activity Recognition
Sina Mokhtarzadeh Azar, Mina Ghadimi Atigh, Ahmad Nickabadi, Alexandre Alahi
A Multi-Stream Convolutional Neural Network Framework for Group Activity Recognition
Sina Mokhtarzadeh Azar, Mina Ghadimi Atigh, Ahmad Nickabadi
Zoom-RNN: A Novel Method for Person Recognition Using Recurrent Neural Networks
Sina Mokhtarzadeh Azar, Sajjad Azami, Mina Ghadimi Atigh, Mohammad Javadi, Ahmad Nickabadi
Supervision
If you are interested in working on Image/Video Generation, feel free to contact me.
Luis Denninger (Msc Student)
Context-aware Camera Controllable Video Generation (2025)
Leon Herbrik (Msc Student)
Generative Episodic Memory (2024)