3D Scene Reconstruction with Neural Radiance Fields (NeRF) Considering Dynamic Illumination Conditions

Скорочена інформація про документ
dc.contributor.authorKolodiazhna, Olena
dc.contributor.authorSavin, Volodymyr
dc.contributor.authorUss, Mykhailo
dc.contributor.authorKussul, Nataliia
dc.date.accessioned2023-11-07T10:47:32Z
dc.date.available2023-11-07T10:47:32Z
dc.date.issued2023
dc.description.abstractThis paper addresses the problem of novel view synthesis using Neural Radiance Fields (NeRF) for scenes with dynamic illumination. NeRF training utilizes photometric consistency loss that is pixel-wise consistency between a set of scene images and intensity values rendered by NeRF. For reflective surfaces, image intensity depends on viewing angle and this effect is taken into account by using ray direction as NeRF input. For scenes with dynamic illumination, image intensity depends not only on position and viewing direction but also on time. We show that this factor affects NeRF training with standard photometric loss function effectively decreasing quality of both image and depth rendering. To cope with this problem, we propose to add time as additional NeRF input. Experiments on ScanNet dataset demonstrate that NeRF with modified input outperforms original model version and renders more consistent 3D structures. Results of this study could be used to improve quality of training data augmentation for depth prediction models (e.g. depth-from-stereo models) for scenes with non-static illumination.uk
dc.format.pagerangePp. 233-238uk
dc.identifier.citation3D Scene Reconstruction with Neural Radiance Fields (NeRF) Considering Dynamic Illumination Conditions / Olena Kolodiazhna, Volodymyr Savin, Mykhailo Uss, Nataliia Kussul // In Proceedings of International Conference on Applied Innovation in IT, (ICAIIT). – 2023. – Pp. 233-238. – Bibliogr.: 19 ref.uk
dc.identifier.doihttps://doi.org/10.25673/101943
dc.identifier.urihttps://ela.kpi.ua/handle/123456789/62039
dc.language.isoenuk
dc.publisherAnhalt University of Applied Sciencesuk
dc.relation.ispartofProceedings of the 11th International Conference on Applied Innovations in IT, (ICAIIT)uk
dc.subjectComputer Visionuk
dc.subjectNeural Radiance Fieldsuk
dc.subjectDynamic Illuminationuk
dc.subjectView Synthesisuk
dc.subject3D Scene Reconstructionuk
dc.title3D Scene Reconstruction with Neural Radiance Fields (NeRF) Considering Dynamic Illumination Conditionsuk
dc.typeArticleuk

Файли

Контейнер файлів
Зараз показуємо 1 - 1 з 1
Ескіз
Назва:
3D_Scene_Reconstruction.pdf
Розмір:
2.05 MB
Формат:
Adobe Portable Document Format
Опис:
Завантажити
Ліцензійна угода
Зараз показуємо 1 - 1 з 1
Ескіз недоступний
Назва:
license.txt
Розмір:
9.1 KB
Формат:
Item-specific license agreed upon to submission
Опис:
Завантажити

Зібрання

Матеріали конференцій, семінарів і т.п. (ММАД)