|
Fast real-time 3D modeling of objects and scenes (for Lay3rs.io)KASHTANOVA Victoriya Development of NeRF- and Diffusion- model based solutions for fast real-time 3D modeling of objects and scenes from video and image databases.
|
Post-graduate projects
|
Physics-Based Deep Learning applied to Cardiology (Thesis)KASHTANOVA Victoriya Thesis : Learning Cardiac Electrophysiological Dynamics with PDE-based Physiological Constraints for Data-Driven Personalized Predictions in Cardiology, under supervision of Maxime Sermesant (Inria, Epione) and Patrick Gallinari (Sorbonne University, LIP6, MLIA).
|
|
Unsupervised 3D Semantic Segmentation and Domain Adaptation (CrossMoDA challenge for MICCAI 2021 Conf.)LY Buntheng, KASHTANOVA Victoriya, YANG Yingyu, MAILLOT Aurelien, NUNEZ-GARSIA Marta and SERMESANT Maxime 6th place in the Cross-Modality Domain Adaptation challenge, the main goal of which was to achieve unsupervised 3D multi-class vestibular schwannoma and cochlea segmentation. Results were published in the Medical Image Analysis journal.
|
Undergraduate projects
|
True face detection (for Ubble.ai)CLIVIO Oscar, CORVISIER Jean-Christophe, KASHTANOVA Victoriya and LOISEAU Romain Solution development for real user authentification against various types of digital fraud, like : high-resolution photos or videos, 3D masks etc.
|
|
CycleGAN analysis (Research project for DL course)KASHTANOVA Victoriya, PESQUEREL Fabien Deep investigation of the CycleGAN model paper : construction, training configurations, used metrics etc. Also studying the impact of the "anchor loss" (we added one matched pair of images and its loss to the unpaired datasets) on the model performance and the ability of the CycleGAN to do a transfer learning.
|
|
Deep Reinforcement Learning agents playing DOOM (Research project for RL and Computer Vision courses)HURAULT Samuel and KASHTANOVA Victoriya Investigation and optimization of two deep Reinforcement Learning frameworks which learn sensorimotor control in partially observable 3D environments.
|
|
Computer vision for serial numbers (for Pzartech.com)BOZOU Sacha, DE SOUSA Philippe, DUMONT Louis and KASHTANOVA Victoriya Solution development for serial number recognition on the mechanical parts.
|
|
|
|
Population based epidemiological modelling (Research project in mathematics)KASHTANOVA Victoriya, supervised by KABANIKHIN Sergey and KRIVOROTKO Olga Knowing that the models of the epidemic spread could be described by systems of nonlinear ODEs whose coefficients characterize the features of population and disease.I worked on the construction and investigation of numerical algorithms for determining these coefficients by the global minimization of the multidimensional target function.
|