Thesis Details
Odhad hloubky pomocí konvolučních neuronových sítí
This thesis deals with depth estimation using convolutional neural networks. I propose a three-part model as a solution to this problem. The model contains a global context network which estimates coarse depth structure of the scene, a gradient network which estimates depth gradients and a refining network which utilizes the outputs of previous two networks to produce the final depth map. Additionally, I present a normalized loss function for training neural networks. Applying normalized loss function results in better estimates of the scene's relative depth structure, however it results in a loss of information about the absolute scale of the scene.
depth estimation, convolutional neural networks, global context network, gradient network, refining network, NYU Depth v2., data augmentation, normalized loss, Caffe
Herout Adam, prof. Ing., Ph.D. (DCGM FIT BUT), člen
Hrdina Jaroslav, doc. Mgr., Ph.D. (DADM FME BUT), člen
Španěl Michal, Ing., Ph.D. (DCGM FIT BUT), člen
Švéda Miroslav, prof. Ing., CSc. (DIFS FIT BUT), člen
Vojnar Tomáš, prof. Ing., Ph.D. (DITS FIT BUT), člen
@mastersthesis{FITMT18852,
author = "J\'{a}n Ivaneck\'{y}",
type = "Master's thesis",
title = "Odhad hloubky pomoc\'{i} konvolu\v{c}n\'{i}ch neuronov\'{y}ch s\'{i}t\'{i}",
school = "Brno University of Technology, Faculty of Information Technology",
year = 2016,
location = "Brno, CZ",
language = "czech",
url = "https://www.fit.vut.cz/study/thesis/18852/"
}