University of Primorska University Library - all departments (UPUK)
13.
Mixed reality and deep learning : augmenting visual information using generative adversarial networks
Šoberl, Domen
This chapter summarizes the theory of Generative Adversarial Networks (GANs), overviews the evolution of GAN methods that have either been used in published Augmented Reality (AR) research or have a ...strong potential for future AR work, and presents interesting use cases of GANs in AR. GAN is one of the most innovative deep learning techniques. Since it was first introduced in 2014, many variations have been proposed. Recent implementations can create photo-realistic high-fidelity visual content that is virtually indiscernible from real-world images. In AR, photo-realism is crucial for the user to perceive the composed reality as belonging to the same world. The composition of virtual objects into the real-world background must be done in a plausible way, with semantically-aware object placement, consistent illumination and convincingly cast shadows. Various GAN architectures were proposed that address one or another of these challenges. The discussed methods are categorized into three distinct groups that correspond to unrelated bodies of research: GANs for image composition, AR face filters, and 3D model generators.
It was not necessary to add the material to the shelf.
Bibliographic material was successfully added on shelf.
Adding bibliographical material on shelf was not successful.
Material is already on the shelf.
Permalink
URL:
Impact factor
Access to the JCR database is permitted only to users from Slovenia. Your current IP address is not on the list of IP addresses with access permission, and authentication with the relevant AAI accout is required.
Year
Impact factor
Edition
Category
Classification
JCR
SNIP
JCR
SNIP
JCR
SNIP
JCR
SNIP
Select the library membership card:
DRS,
in which the journal is indexed
Database name
Field
Year
Links to authors' personal bibliographies
Links to information on researchers in the SICRIS system
Subject headings in COBISS General List of Subject Headings
Select pickup location
The material from the parent unit is free. If the material is delivered to the pickup location from another unit, the library may charge you for this service.
