Towards Visual Training Set Generation Framework

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61988987%3A17610%2F17%3AA1901OX9" target="_blank" >RIV/61988987:17610/17:A1901OX9 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1007/978-3-319-59147-6_63" target="_blank" >http://dx.doi.org/10.1007/978-3-319-59147-6_63</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-319-59147-6_63" target="_blank" >10.1007/978-3-319-59147-6_63</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Towards Visual Training Set Generation Framework

Popis výsledku v původním jazyce

Performance of trained computer vision algorithms is largely dependent on amounts of data, on which it is trained. Creating large labeled datasets is very expensive, and therefore many researchers use synthetically generated images with automatic annotations. To this purpose we have created a general framework, which allows researchers to generate practically infinite amount of images from a set of 3D models, textures and material settings. We leverage Voxel Cone Tracing technology implemented by NVIDIA to render photorealistic images in realtime without any kind of precomputation. We have build this framework with two use cases in mind: (i) for real world applications, where a database with synthetically generated images could compensate for small or non existent datasets, and (ii) for empirical testing of theoretical ideas by creating training sets with known inner structure.

Název v anglickém jazyce

Towards Visual Training Set Generation Framework

Popis výsledku anglicky

Performance of trained computer vision algorithms is largely dependent on amounts of data, on which it is trained. Creating large labeled datasets is very expensive, and therefore many researchers use synthetically generated images with automatic annotations. To this purpose we have created a general framework, which allows researchers to generate practically infinite amount of images from a set of 3D models, textures and material settings. We leverage Voxel Cone Tracing technology implemented by NVIDIA to render photorealistic images in realtime without any kind of precomputation. We have build this framework with two use cases in mind: (i) for real world applications, where a database with synthetically generated images could compensate for small or non existent datasets, and (ii) for empirical testing of theoretical ideas by creating training sets with known inner structure.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10200 - Computer and information sciences

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2017

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Advances in Computational Intelligence

ISBN

978-3-319-59146-9

ISSN

—

e-ISSN

—

Počet stran výsledku

12

Strana od-do

747-758

Název nakladatele

Springer Verlag

Místo vydání

Cadiz

Místo konání akce

Cadiz

Datum konání akce

14. 6. 2017

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000443108700063