Name: Alexey Artemov
Position: Post Doc
E-Mail: alexey.artemov@tum.de
Phone: TBD
Room No: 02.07.039

Bio

Hi! I am Alexey, a postdoc researcher at TUM Visual Computing Lab. Previously to joining TUM, I was a researcher at ADASE laboratory, CDISE Skoltech, advised by Associate Professor Evgeny Burnaev and Adjunct Professor Denis Zorin. I obtained my Ph.D. in 2017 from Institute for Systems Analysis of Russian Academy of Sciences (ISA RAS) under the supervision of Evgeny Burnaev. In 2012—2017, I served as a research engineer at Yandex, the Moscow-based internet giant, where I developed software systems for web search, computer vision, and autonomous driving. See more in my CV.
My research interests include 3D scene and shape reconstruction and digital geometry processing, where I work on improving the geometry processing pipeline with deep learning accelerated algorithms. In 2021, I was honoured to receive the Ilya Segalovich Award for academic advisors.
For more details, please visit my personal webpage at https://artonson.github.io.

Research Interest

3D reconstruction, datasets and frameworks, cad deep learning

Publications

2024

PRS: Sharp Feature Priors for Resolution-Free Surface Remeshing
Natalia Soboleva, Olga Gorbunova, Maria Ivanova, Evgeny Burnaev, Matthias Nießner, Denis Zorin, Alexey Artemov
CVPR 2024
We present a data-driven approach for automatic feature detection and remeshing in coarse, aliased mesh reconstructions. Our method estimates sharp geometric features and identifies surface meshing artifacts in 3D surface mesh models of arbitrary resolution, obtaining feature and surface improvement fields. We further reconstruct and remesh sharp geometric features in 3D surface meshes by incorporating our fields as priors for local surface remeshing.
[video][bibtex][project page]

MeshGPT: Generating Triangle Meshes with Decoder-Only Transformers
Yawar Siddiqui, Antonio Alliegro, Alexey Artemov, Tatiana Tommasi, Daniele Sirigatti, Vladislav Rosov, Angela Dai, Matthias Nießner
CVPR 2024
MeshGPT creates triangle meshes by autoregressively sampling from a transformer model that has been trained to produce tokens from a learned geometric vocabulary. Our method generates clean, coherent, and compact meshes, characterized by sharp edges and high fidelity.
[video][bibtex][project page]

2020

CAD-Deform: Deformable Fitting of CAD Models to 3D Scans
Vladislav Ishimtsev, Alexey Bokhovkin, Alexey Artemov, Savva Ignatiev, Matthias Nießner, Denis Zorin, Evgeny Burnaev
ECCV 2020
We propose CAD-Deform, a method which obtains more accurate CAD-to-scan fits by non-rigidly deforming retrieved CAD models.
[code][bibtex][project page]