3D reconstruction of incomplete archaeological objects using a generative adversarial network

Renato Hermoza, Ivan Sipiran

Producción científica: Capítulo del libro/informe/acta de congresoContribución a la conferenciarevisión exhaustiva

33 Citas (Scopus)

Resumen

We introduce a data-driven approach to aid the repairing and conservation of archaeological objects: ORGAN, an object reconstruction generative adversarial network (GAN). By using an encoder-decoder 3D deep neural network on a GAN architecture, and combining two loss objectives: a completion loss and an Improved Wasserstein GAN loss, we can train a network to effectively predict the missing geometry of damaged objects. As archaeological objects can greatly differ between them, the network is conditioned on a variable, which can be a culture, a region or any metadata of the object. In our results, we show that our method can recover most of the information from damaged objects, even in cases where more than half of the voxels are missing, without producing many errors.

Idioma originalInglés
Título de la publicación alojadaProceedings of Computer Graphics International, CGI 2018
EditorialAssociation for Computing Machinery
Páginas5-11
Número de páginas7
ISBN (versión digital)1595930361, 9781450364010
DOI
EstadoPublicada - 11 jun. 2018
Evento2018 Computer Graphics International Conference, CGI 2018 - Bintan, Indonesia
Duración: 11 jun. 201814 jun. 2018

Serie de la publicación

NombreACM International Conference Proceeding Series

Conferencia

Conferencia2018 Computer Graphics International Conference, CGI 2018
País/TerritorioIndonesia
CiudadBintan
Período11/06/1814/06/18

Huella

Profundice en los temas de investigación de '3D reconstruction of incomplete archaeological objects using a generative adversarial network'. En conjunto forman una huella única.

Citar esto