We introduce a new method for non-rigid registration of 3D human shapes. Our proposed pipeline builds upon a given parametric model of the human, and makes use of the functional map representation for encoding and inferring shape maps throughout the registration process. This combination endows our method with robustness to a large variety of nuisances observed in practical settings, including non-isometric transformations, downsampling, topological noise and occlusions; further, the pipeline can be applied invariably across different shape representations (e.g. meshes and point clouds), and in the presence of (even dramatic) missing parts such as those arising in real-world depth sensing applications. We showcase our method on a selection of challenging tasks, demonstrating results in line with, or even surpassing, state-of-the-art methods in the respective areas.

Marin, R., Melzi, S., Rodola, E., Castellani, U. (2020). FARM: Functional Automatic Registration Method for 3D Human Bodies. COMPUTER GRAPHICS FORUM, 39(1 (February 2020)), 160-173 [10.1111/cgf.13751].

FARM: Functional Automatic Registration Method for 3D Human Bodies

Melzi S.
;
2020

Abstract

We introduce a new method for non-rigid registration of 3D human shapes. Our proposed pipeline builds upon a given parametric model of the human, and makes use of the functional map representation for encoding and inferring shape maps throughout the registration process. This combination endows our method with robustness to a large variety of nuisances observed in practical settings, including non-isometric transformations, downsampling, topological noise and occlusions; further, the pipeline can be applied invariably across different shape representations (e.g. meshes and point clouds), and in the presence of (even dramatic) missing parts such as those arising in real-world depth sensing applications. We showcase our method on a selection of challenging tasks, demonstrating results in line with, or even surpassing, state-of-the-art methods in the respective areas.
Articolo in rivista - Articolo scientifico
3D shape matching; digital geometry processing; geometric modelling; modelling; Shape analysis; • Computing methodologies → Shape modelling;
English
18-giu-2019
2020
39
1 (February 2020)
160
173
reserved
Marin, R., Melzi, S., Rodola, E., Castellani, U. (2020). FARM: Functional Automatic Registration Method for 3D Human Bodies. COMPUTER GRAPHICS FORUM, 39(1 (February 2020)), 160-173 [10.1111/cgf.13751].
File in questo prodotto:
File Dimensione Formato  
Marin_FARM_2020.pdf

Solo gestori archivio

Dimensione 2.72 MB
Formato Adobe PDF
2.72 MB Adobe PDF   Visualizza/Apri   Richiedi una copia

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/10281/350552
Citazioni
  • Scopus 47
  • ???jsp.display-item.citation.isi??? 28
Social impact