Search Results for author: Atanas Mirchev

Found 7 papers, 0 papers with code

Tracking and Planning with Spatial World Models

no code implementations25 Jan 2022 Baris Kayalibay, Atanas Mirchev, Patrick van der Smagt, Justin Bayer

We introduce a method for real-time navigation and tracking with differentiably rendered world models.

Pose Estimation

Mind the Gap when Conditioning Amortised Inference in Sequential Latent-Variable Models

no code implementations ICLR 2021 Justin Bayer, Maximilian Soelch, Atanas Mirchev, Baris Kayalibay, Patrick van der Smagt

Amortised inference enables scalable learning of sequential latent-variable models (LVMs) with the evidence lower bound (ELBO).

Variational State-Space Models for Localisation and Dense 3D Mapping in 6 DoF

no code implementations ICLR 2021 Atanas Mirchev, Baris Kayalibay, Patrick van der Smagt, Justin Bayer

We solve the problem of 6-DoF localisation and 3D dense reconstruction in spatial environments as approximate Bayesian inference in a deep state-space model.

Bayesian Inference Variational Inference

Classification of sparsely labeled spatio-temporal data through semi-supervised adversarial learning

no code implementations26 Jan 2018 Atanas Mirchev, Seyed-Ahmad Ahmadi

In recent years, Generative Adversarial Networks (GAN) have emerged as a powerful method for learning the mapping from noisy latent spaces to realistic data samples in high-dimensional space.

General Classification Retrieval

3D Deep Learning for Biological Function Prediction from Physical Fields

no code implementations13 Apr 2017 Vladimir Golkov, Marcin J. Skwark, Atanas Mirchev, Georgi Dikov, Alexander R. Geanes, Jeffrey Mendenhall, Jens Meiler, Daniel Cremers

In this paper, we show that deep learning can predict biological function of molecules directly from their raw 3D approximated electron density and electrostatic potential fields.

Cannot find the paper you are looking for? You can Submit a new open access paper.