IVL-SYNTHSFM-v2: A synthetic dataset with exact ground truth for the evaluation of 3D reconstruction pipelines

This article presents a dataset with 4000 synthetic images portraying five 3D models from different viewpoints under varying lighting conditions. Depth of field and motion blur have also been used to generate realistic images. For each object, 8 scenes with different combinations of lighting, depth...

Descripción completa

Detalles Bibliográficos
Autores principales: Marelli, Davide, Bianco, Simone, Ciocca, Gianluigi
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Elsevier 2019
Materias:
Computer Science
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6971370/
https://www.ncbi.nlm.nih.gov/pubmed/31993461
http://dx.doi.org/10.1016/j.dib.2019.105041

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6971370/
https://www.ncbi.nlm.nih.gov/pubmed/31993461
http://dx.doi.org/10.1016/j.dib.2019.105041

Ejemplares similares