Scholar
Artem Sevastopolsky
Google Scholar ID: fTSCTYQAAAAJ
Apple
Citations & Impact
Citations
1,343
H-index
10
i10-index
10
Publications
18
Co-authors
16
list available
Publications
Resume (English only)
Academic Achievements
- 1. DenseMarks: Learning Canonical Embeddings for Human Heads Images via Point Tracks
- 2. GeomHair: Reconstruction of Hair Strands from Colorless 3D Scans
- 3. GaussianSpeech: Audio-Driven Gaussian Avatars
- 4. 3DGH: 3D Head Generation with Composable Hair and Face
- 5. Avat3r: Large Animatable Gaussian Reconstruction Model for High-fidelity 3D Head Avatars
- 6. HeadCraft: Modeling High-Detail Shape Variations for Animated 3DMMs
Research Experience
- Worked on various projects at Samsung and Skoltech, including realistic differentiable rendering of 3D point clouds, human photo-to-texture synthesis, differentiable warping methods for view resynthesis, and other projects. Previously, more into medical imaging at Lomonosov Moscow State University and in the industry.
Education
- Ph.D.: TUM (Advisor: Prof. Matthias Nießner); M.Sc.: Skoltech (Advisor: Prof. Victor Lempitsky)
Background
- Currently a research engineer at Apple Munich Vision Lab. Previously, a Ph.D. student at TUM (Visual Computing & AI lab led by prof. Matthias Nießner). Prior to that, worked as a deep learning engineer at the Vision, Learning and Telepresence lab at Samsung AI Center Moscow and studied at Skoltech under supervision of prof. Victor Lempitsky. Recently, a research intern at Meta Reality Labs, Codec Avatars Team. Main research interest is in the applications of computer vision to 3D computer graphics and rendering of Digital Humans.
Miscellany
- Contact information and links to Google Scholar, GitHub, LinkedIn, and Twitter are provided on the personal website.
