Cultural Heritage 3D Reconstruction with Diffusion Networks

Pablo Jaramillo, Ivan Sipiran

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

Resumen

This article explores the use of recent generative AI algorithms for repairing cultural heritage objects, leveraging a conditional diffusion model designed to reconstruct 3D point clouds effectively. Our study evaluates the model’s performance across general and cultural heritage-specific settings. Results indicate that, with considerations for object variability, the diffusion model can accurately reproduce cultural heritage geometries. Despite encountering challenges like data diversity and outlier sensitivity, the model demonstrates significant potential in artifact restoration research. This work lays groundwork for advancing restoration methodologies for ancient artifacts using AI technologies (The dataset is available in: https://github.com/PJaramilloV/Precolombian-Dataset, and the code in https://github.com/PJaramilloV/pcdiff-method).

Idioma originalInglés
Título de la publicación alojadaComputer Vision – ECCV 2024 Workshops, Proceedings
EditoresAlessio Del Bue, Cristian Canton, Jordi Pont-Tuset, Tatiana Tommasi
EditorialSpringer Science and Business Media Deutschland GmbH
Páginas104-117
Número de páginas14
ISBN (versión impresa)9783031915710
DOI
EstadoPublicada - 2025
Publicado de forma externa
EventoWorkshops that were held in conjunction with the 18th European Conference on Computer Vision, ECCV 2024 - Milan, Italia
Duración: 29 set. 20244 oct. 2024

Serie de la publicación

NombreLecture Notes in Computer Science
Volumen15628 LNCS
ISSN (versión impresa)0302-9743
ISSN (versión digital)1611-3349

Conferencia

ConferenciaWorkshops that were held in conjunction with the 18th European Conference on Computer Vision, ECCV 2024
País/TerritorioItalia
CiudadMilan
Período29/09/244/10/24

Huella

Profundice en los temas de investigación de 'Cultural Heritage 3D Reconstruction with Diffusion Networks'. En conjunto forman una huella única.

Citar esto