Maria Korosteleva

Maria Korosteleva

Postdoctoral Researcher

IGL | ETH Zurich

Biography

I’m a postdoctoral researcher at Interactive Geometry Lab in ETH Zurich with Professor Olga Sorkine-Hornung. I earned by BSc ans MSc in the area of Applied Mathematics and Computer Science from Lomonosov Moscow State university. Later, I received my Ph.D. Degree from LAVA Lab, KAIST, under supervision of Professor Sung-Hee Lee.

My research interests revolve around the application of AI to geometry processing, shape generation, and reconstruction, specifically in the areas of Digital garments and Virtual humans. I find inspiration in science, creative fields, and stunning visual masterpieces.

Download my resumé.

Interests
  • Artificial Intelligence
  • Geometry Processing
  • Virtual Garments
Education

  • PhD in Computer Graphics and Artificial Intelligence, 2022

    KAIST

  • BSc + MSc in Applied Mathematics and Computer Science, 2015

    Lomonosov Moscow State University

Publications

GarmentCodeData: A Dataset of 3D Made-to-Measure Garments With Sewing Patterns
ECCV 2024. A large-scale dataset of 115,000 3D garment designs fitted across 5000 body shapes.
Maria Korosteleva, Timur Levent Kesdogan, Fabian Kemper, Stephan Wenninger, Jasmin Koller, Yuhan Zhang, Mario Botsch, Olga Sorkine-Hornung
Cite Project arXiv PDF Dataset (v2) Code
GarmentCodeData: A Dataset of 3D Made-to-Measure Garments With Sewing Patterns
GarmentCode: Programming Parametric Sewing Patterns
SIGGRAPH Asia 2023 (Journal paper). A modular programming framework for designing parametric sewing patterns
Maria Korosteleva, Olga Sorkine-Hornung
Cite DOI Project arXiv PDF Code Demo
GarmentCode: Programming Parametric Sewing Patterns
NeuralTailor: Reconstructing Sewing Pattern Structures from 3D Point Clouds of Garments
SIGGRAPH 2022 (Journal paper). NeuralTailor processes a variety of garment types and even generalizes to the ones unseen during training.
Maria Korosteleva, Sung-Hee Lee
Cite DOI arXiv PDF Code
NeuralTailor: Reconstructing Sewing Pattern Structures from 3D Point Clouds of Garments
Generating Datasets of 3D Garments with Sewing Patterns
NeurIPS Track on Datasets and Benchmarks 2021. A data generator and a design-focused dataset with 20 000 garment design samples with a variety of garment types.
Maria Korosteleva, Sung-Hee Lee
Cite arXiv PDF Dataset Code
Generating Datasets of 3D Garments with Sewing Patterns
Estimating Garment Patterns from Static Scan Data
Computer Graphics Forum 2021. A framework to convert a static 3D scan of a person into a controllable avatar with responsive garments
Seungbae Bang, Maria Korosteleva, Sung-Hee Lee
Cite DOI Shape Estimation Code
Estimating Garment Patterns from Static Scan Data

Awards

KCGS 2022
CLO Award
KCGS 2022 Jul 2022
Awarded by CLO Virtual Fashion & KCGS 2022 for outstanding papers on Digital Garments for NeuralTailor project

Experience

 
 
 
 
 
IGL at ETH Zurich
Postdoctoral Researcher
IGL at ETH Zurich
Sep 2022 – Present Switzerland
In collaboration with Prof. Dr. Olga Sorkine-Hornung
 
 
 
 
 
Meta Platforms, Inc.
Research Intern at Reality Labs Research
Meta Platforms, Inc.
Aug 2021 – Dec 2021 Redmond, US (Remote)
Developed a robust solution for volumetric segmentation with DL-based CV methods
 
 
 
 
 
LAVA Lab at KAIST
Research Assistant
LAVA Lab at KAIST
Feb 2018 – Aug 2022 Daejeon, South Korea
  • Research projects on realistic virtual avatars for humans
  • Numerical optimization, 3D and Structured Deep Learning