- University of Tübingen
Maria-von-Linden Strasse 1
72076 - A513
- i.petrov@uni-tuebingen.de
About Me
I am a Ph.D. candidate at the University of Tübingen and the Tübingen AI Center, supervised by Prof. Dr. Gerard Pons-Moll. My research is in 3D computer vision and digital humans, focusing on modeling human-object interactions, human motion, and egocentric vision.
I obtained my B.Sc. and M.Sc. from Moscow State University, where I worked on human shape and pose reconstruction from images. Before starting my Ph.D., I worked at Samsung AI Center on interactive image segmentation.




Publications

Ilya A. Petrov,
Vladimir Guzov,
Riccardo Marin,
Emre Aksan,
Xu Chen,
Daniel Cremers,
Thabo Beeler,
Gerard Pons-Moll
ECHO: Ego-Centric modeling of Human-Object interactions
in European Conference on Computer Vision, 2026.
ECHO: Ego-Centric modeling of Human-Object interactions
in European Conference on Computer Vision, 2026.

Nikos Athanasiou,
Ilya A. Petrov,
Angela Yao,
Shugao Ma,
Eric Sauser,
Edoardo Remeli,
Shreyas Hampali,
Johannes Schönberger,
Fadime Sener,
Bugra Tekin
TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction
in European Conference on Computer Vision, 2026.
TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction
in European Conference on Computer Vision, 2026.

Ilya A. Petrov,
Riccardo Marin,
Julian Chibane,
Gerard Pons-Moll
TriDi: Trilateral Diffusion of 3D Humans, Objects, and Interactions
in Proceedings of the IEEE/CVF International Conference on Computer Vision, 2025.
TriDi: Trilateral Diffusion of 3D Humans, Objects, and Interactions
in Proceedings of the IEEE/CVF International Conference on Computer Vision, 2025.

Xiaohan Zhang,
Bharat Lal Bhatnagar,
Sebastian Starke,
Ilya A. Petrov,
Vladimir Guzov,
Helisa Dhamo,
Eduardo Pérez Pellitero,
Gerard Pons-Moll
FORCE: Dataset and Method for Intuitive Physics Guided Human-object Interaction
in International Conference on 3D Vision (3DV), 2025.
FORCE: Dataset and Method for Intuitive Physics Guided Human-object Interaction
in International Conference on 3D Vision (3DV), 2025.

Vladimir Guzov,
Ilya A. Petrov,
Gerard Pons-Moll
Blendify - Python rendering framework for Blender
in Arxiv, 2024.
Blendify - Python rendering framework for Blender
in Arxiv, 2024.

Ilya A. Petrov,
Riccardo Marin,
Julian Chibane,
Gerard Pons-Moll
Object pop-up: Can we infer 3D objects and their poses from human interactions alone?
in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023.
Object pop-up: Can we infer 3D objects and their poses from human interactions alone?
in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023.

Bharat Lal Bhatnagar,
Xianghui Xie,
Ilya A. Petrov,
Cristian Sminchisescu,
Christian Theobalt,
Gerard Pons-Moll
BEHAVE: Dataset and Method for Tracking Human Object Interactions
in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022.
*The first two authors contributed equally.
BEHAVE: Dataset and Method for Tracking Human Object Interactions
in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022.
*The first two authors contributed equally.

Konstantin Sofiiuk,
Ilya A. Petrov,
Olga Barinova,
Anton Konushin
F-BRS: Rethinking Backpropagating Refinement for Interactive Segmentation
in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020.
Oral
F-BRS: Rethinking Backpropagating Refinement for Interactive Segmentation
in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020.
Oral