Vanessa Sklyarova

I am a Ph.D. student (2023-) at the Max Planck ETH Center for Learning Systems (CLS), jointly supervised by Justus Thies (MPI), Michael Black (MPI), Otmar Hilliges (ETH) and Marc Pollefeys (ETH). Before that, I worked as a Research Engineer at Samsung AI Center (2021-2023). I obtained my Master's degree (2020-2022) in Data Science from a joint program between Skolkovo Institute of Science and Technology and Moscow Institute of Physics and Technology.

My interests lie at the intersection of Computer Graphics and Computer Vision. I am interested in creating photorealistic human avatars. Currently, I am focused on realistic hair reconstruction and rendering.

Email  /  GitHub /  Twitter  /  Linkedin

Publications

Joker: Conditional 3D Head Synthesis with Extreme Facial Expressions
Malte Prinzler, Egor Zakharov, Vanessa Sklyarova, Berna Kabadayi, Justus Thies
International Conference on 3D Vision (3DV) 2025
Project page / To be soon / video / arXiv

One-shot realistic 3D head avatars with extreme facial expressions.

Gaussian Haircut: Human Hair Reconstruction with Strand-Aligned 3D Gaussians
Egor Zakharov, Vanessa Sklyarova, Michael J. Black, Giljoo Nam, Justus Thies, Otmar Hilliges
European Conference on Computer Vision (ECCV) 2024
Project page / Code / video / arXiv

Reconstruction and rendering of strand-based hairstyles from a monocular video using Gaussian splatting.

HAAR: Text-Conditioned Generative Model of 3D Strand-based Human Hairstyles
Vanessa Sklyarova, Egor Zakharov, Otmar Hilliges, Michael J. Black, Justus Thies
Computer Vision and Pattern Recognition (CVPR) 2024
Project page / Code / video / arXiv

Text conditional generative model for strand-based 3D hairstyles.

Neural Haircut: Prior-Guided Strand-Based Hair Reconstruction
Vanessa Sklyarova, Jenya Chelishev, Andreea Dogaru, Igor Medvedev, Victor Lempitsky, Egor Zakharov
International Conference on Computer Vision (ICCV) 2023 (Oral presentation)
Project page / Code / video / arXiv

Realistic strand-based hair reconstruction using multiview data or monocular video.

Realistic One-shot Mesh-based Head Avatars
Taras Khakhulin, Vanessa Sklyarova, Victor Lempitsky, Egor Zakharov
European Conference on Computer Vision (ECCV) 2022
Project page / Code / arXiv

Generation of animatable avatar from a single image with coarse hair mesh and neural rendering.


adapted from Jon Barron's awesome webpage