Publications de Timur Bagautdinov

DeepMesh: Differentiable Iso-Surface Extraction

Pascal Fua, Benoît Alain René Guillard, Pierre Bruno Baqué, Timur Bagautdinov, Edoardo Remelli, Pierre Mathieu Yvernay

2024

Masksembles for Uncertainty Estimation

Pascal Fua, Pierre Bruno Baqué, Nikita Durasov, Timur Bagautdinov

Deep neural networks have amply demonstrated their prowess but estimating the reliability of their predictions remains challenging. Deep Ensembles are widely considered as being one of the best methods for generating uncertainty estimates but are very expe ...

2021

MeshSDF: Differentiable Iso-Surface Extraction

Pascal Fua, Benoît Alain René Guillard, Pierre Bruno Baqué, Timur Bagautdinov, Edoardo Remelli, Artem Lukoianov

2020

Modeling Facial Geometry using Compositional VAEs

Pascal Fua, Timur Bagautdinov, Chenglei Wu

We propose a method for learning non-linear face geometry representations using deep generative models. Our model is a variational autoencoder with multiple levels of hidden variables where lower layers capture global geometry and higher ones encode more l ...

2018

Variational Methods for Human Modeling

Timur Bagautdinov

A large part of computer vision research is devoted to building models and algorithms aimed at understanding human appearance and behaviour from images and videos. Ultimately, we want to build automated systems that are at least as capable as people when i ...

EPFL2018

Principled Parallel Mean-Field Inference for Discrete Random Fields

Pascal Fua, François Fleuret, Pierre Bruno Baqué, Timur Bagautdinov

Mean-field variational inference is one of the most popular approaches to inference in discrete random fields. Standard mean-field optimization is based on coordinate descent and in many situations can be impractical. Thus, in practice, various parallel te ...

2016

Progressive Geometric Algorithms

Timur Bagautdinov

Progressive algorithms are algorithms that, on the way to computing a complete solution to the problem at hand, output intermediate solutions that approximate the complete solution increasingly well. We present a framework for analyzing such algorithms, an ...

Carleton Univ, Dept Mathematics & Statistics2015

Probability Occupancy Maps for Occluded Depth Images

Pascal Fua, François Fleuret, Timur Bagautdinov

2015