Ears are a particularly difficult region of the human face to model, not only due to the non-rigid deformations existing between shapes but also to the challenges in processing the retrieved data. The first step towards obtaining a good model is to have complete scans in correspondence, but these usually present a higher amount of occlusions, noise and outliers when compared to most face regions, thus requiring a specific procedure. Therefore, we propose a complete pipeline taking as input unordered 3D point clouds with the aforementioned problems, and producing as output a dataset in correspondence, with completion of the missing data. We provide a comparison of several state-of-the-art registration and shape completion methods, concluding on the best choice for each of the steps.

From noisy point clouds to complete ear shapes: unsupervised pipeline / F. Marreiros Malveiro Valdeira, R. Ferreira, A. Micheletti, C. Soares. - In: IEEE ACCESS. - ISSN 2169-3536. - 9(2021), pp. 127720-127734. [10.1109/ACCESS.2021.3111811]

From noisy point clouds to complete ear shapes: unsupervised pipeline

F. Marreiros Malveiro Valdeira
Primo
;
A. Micheletti;
2021

Abstract

Ears are a particularly difficult region of the human face to model, not only due to the non-rigid deformations existing between shapes but also to the challenges in processing the retrieved data. The first step towards obtaining a good model is to have complete scans in correspondence, but these usually present a higher amount of occlusions, noise and outliers when compared to most face regions, thus requiring a specific procedure. Therefore, we propose a complete pipeline taking as input unordered 3D point clouds with the aforementioned problems, and producing as output a dataset in correspondence, with completion of the missing data. We provide a comparison of several state-of-the-art registration and shape completion methods, concluding on the best choice for each of the steps.
3D morphable model; ear shape modeling; point set registration
Settore MAT/06 - Probabilita' e Statistica Matematica
Settore INF/01 - Informatica
Settore SECS-S/01 - Statistica
Big Data Challenges for Mathematics (BIGMATH)
Article (author)
File in questo prodotto:
File Dimensione Formato  
Published-From_Noisy_Point_Clouds_to_Complete_Ear_Shapes_Unsupervised_Pipeline.pdf

accesso aperto

Descrizione: Articolo principale
Tipologia: Publisher's version/PDF
Dimensione 4 MB
Formato Adobe PDF
4 MB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

Caricamento pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/2434/869818
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? 0
social impact