Search Results for author: Georgi Dikov

Found 6 papers, 2 papers with code

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.

Bayesian Learning of Neural Network Architectures

1 code implementation14 Jan 2019 Georgi Dikov, Patrick van der Smagt, Justin Bayer

In this paper we propose a Bayesian method for estimating architectural parameters of neural networks, namely layer size and network depth.

Neural Architecture Search

Calibrated Adversarial Refinement for Stochastic Semantic Segmentation

3 code implementations ICCV 2021 Elias Kassapis, Georgi Dikov, Deepak K. Gupta, Cedric Nugteren

To this end, we propose a novel two-stage, cascaded approach for calibrated adversarial refinement: (i) a standard segmentation network is trained with categorical cross entropy to predict a pixelwise probability distribution over semantic classes and (ii) an adversarially trained stochastic network is used to model the inter-pixel correlations to refine the output of the first network into coherent samples.

Semantic Segmentation valid

DG-Recon: Depth-Guided Neural 3D Scene Reconstruction

no code implementations ICCV 2023 Jihong Ju, Ching Wei Tseng, Oleksandr Bailo, Georgi Dikov, Mohsen Ghafoorian

A key challenge in neural 3D scene reconstruction from monocular images is to fuse features back projected from various views without any depth or occlusion information.

3D Reconstruction 3D Scene Reconstruction

3D Distillation: Improving Self-Supervised Monocular Depth Estimation on Reflective Surfaces

no code implementations ICCV 2023 Xuepeng Shi, Georgi Dikov, Gerhard Reitmayr, Tae-Kyun Kim, Mohsen Ghafoorian

Self-supervised monocular depth estimation (SSMDE) aims at predicting the dense depth maps of monocular images, by learning to minimize a photometric loss using spatially neighboring image pairs during training.

Monocular Depth Estimation

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