Full metadata record
DC poleHodnotaJazyk
dc.contributor.authorMiller, Markus
dc.contributor.authorRonczka, Stefan
dc.contributor.authorNischwitz, Alfred
dc.contributor.authorRüdiger, Westermann
dc.contributor.editorSkala, Václav
dc.date.accessioned2022-09-01T11:11:19Z
dc.date.available2022-09-01T11:11:19Z
dc.date.issued2022
dc.identifier.citationWSCG 2022: full papers proceedings: 30. International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision, p. 189-198.en
dc.identifier.isbn978-80-86943-33-6
dc.identifier.issn2464-4617
dc.identifier.urihttp://hdl.handle.net/11025/49594
dc.format10 s.cs
dc.format.mimetypeapplication/pdf
dc.language.isoenen
dc.publisherVáclav Skala - UNION Agencyen
dc.rights© Václav Skala - UNION Agencyen
dc.subjectsvětlocs
dc.subjectsměrcs
dc.subjectodhadcs
dc.subjectrekonstrukcecs
dc.subjectvysvětlitelná AIcs
dc.subjectfotometrickýcs
dc.subjectregistracecs
dc.subjecthluboké učenícs
dc.titleLight Direction Reconstruction Analysis and Improvement using XAI and CGen
dc.typeconferenceObjecten
dc.rights.accessopenAccessen
dc.type.versionpublishedVersionen
dc.description.abstract-translatedWith rapid advances in the field of deep learning, explainable artificial intelligence (XAI) methods were introduced to gain insight into internal procedures of deep neural networks. Information gathered by XAI methods can help to identify shortcomings in network architectures and image datasets. Recent studies, however, advise to handle XAI interpretations with care, as they can be unreliable. Due to this unreliability, this study uses meta information that is produced when applying XAI to enhance the architecture – and thus the prediction performance – of a recently published regression model. This model aimed to contribute to solving the photometric registration problem in the field of augmented reality by regressing the dominant light direction in a scene. Bypassing misleading XAI interpretations, the influence of synthetic training data, generated with different rendering techniques, is further- more evaluated empirically. In conclusion, this study demonstrates how the prediction performance of the recently published model can be increased by improving the network architecture and training dataset.en
dc.subject.translatedlighten
dc.subject.translateddirectionen
dc.subject.translatedestimationen
dc.subject.translatedreconstructionen
dc.subject.translatedexplainable AIen
dc.subject.translatedphotometricen
dc.subject.translatedregistrationen
dc.subject.translateddeep learningen
dc.identifier.doihttps://www.doi.org/10.24132/CSRN.3201.24
dc.type.statusPeer-revieweden
Vyskytuje se v kolekcích:WSCG 2022: Full Papers Proceedings

Soubory připojené k záznamu:
Soubor Popis VelikostFormát 
C53-full.pdfPlný text1,81 MBAdobe PDFZobrazit/otevřít
Zobrazit minimální záznam Zobrazit statistiky


Použijte tento identifikátor k citaci nebo jako odkaz na tento záznam: http://hdl.handle.net/11025/49594

Všechny záznamy v DSpace jsou chráněny autorskými právy, všechna práva vyhrazena.

hledání
navigace
  1. DSpace at University of West Bohemia
  2. Publikace ZČU / UWB Publications
  3. Sborníky ZČU / UWB Proceedings
  4. WSCG: Full Papers
  5. WSCG 2022: Full Papers Proceedings