MatchMakerNet: Enabling Fragment Matching for Cultural Heritage Analysis

Ariana M. Villegas-Suarez, Cristian Lopez, Ivan Sipiran

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

Resumen

Automating the reassembly of fragmented objects is a complex task with applications in cultural heritage preservation, paleontology, and medicine. However, the matching subtask of the reassembly process has received limited attention, despite its crucial role in reducing the alignment search space. To address this gap, we propose Match-MakerNet, a network architecture designed to automate the pairing of object fragments for reassembly. By taking two point clouds as input and leveraging graph convolution alongside a simplified version of DGCNN, MatchMakerNet achieves remarkable results. After training on the Artifact (synthetic) dataset, we achieve an accuracy of 87.31% in all-to-all comparisons between the fragments. In addition, it demonstrates robust generalization capabilities, achieving 86.93% accuracy on the Everyday (synthetic) dataset and 83.03% on the Puzzles 3D (real-world) dataset. These findings highlight the effectiveness and versatility of Match-MakerNet in solving the matching subtask.

Idioma originalInglés
Título de la publicación alojadaProceedings - 2023 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2023
EditorialInstitute of Electrical and Electronics Engineers Inc.
Páginas1624-1633
Número de páginas10
ISBN (versión digital)9798350307443
DOI
EstadoPublicada - 2023
Publicado de forma externa
Evento2023 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2023 - Paris, Francia
Duración: 2 oct. 20236 oct. 2023

Serie de la publicación

NombreProceedings - 2023 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2023

Conferencia

Conferencia2023 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2023
País/TerritorioFrancia
CiudadParis
Período2/10/236/10/23

Huella

Profundice en los temas de investigación de 'MatchMakerNet: Enabling Fragment Matching for Cultural Heritage Analysis'. En conjunto forman una huella única.

Citar esto