Surface registration is a fundamental step in the reconstruction of three-dimensional objects. This is typically a two-step process where an initial coarse motion estimation is followed by a refinement step that almost invariably is some variant of Iterative Closest Point (ICP), which iteratively minimizes a distance function measured between pairs of selected neighboring points. The selection of relevant points on one surface to match against points on the other surface is an important issue in any efficient implementation of ICP, with strong implications both on the convergence speed and on the quality of the final alignment. This is due to the fact that typically on a surface there are a lot of low-curvature points that scarcely constrain the rigid transformation and an order of magnitude less descriptive points that are more relevant for finding the correct alignment. This results in a tendency of surfaces to "overfit" noise on low-curvature areas sliding away from the correct alignment. In this paper we propose a novel relevant-point sampling approach for ICP based on the idea that points in an area of great change constrain the transformation more and thus should be sampled with higher frequency. Experimental evaluations confront the alignment accuracy obtained with the proposed approach with those obtained with the commonly adopted uniform subsampling and normal-space sampling strategies. © 2011 IEEE.

Sampling relevant points for surface registration / Torsello, Andrea; Rodolà, Emanuele; Albarelli, Andrea. - (2011), pp. 290-295. (Intervento presentato al convegno 2011 International Conference on 3D Imaging, Modeling, Processing, Visualization and Transmission, 3DIMPVT 2011 tenutosi a Hangzhou; China) [10.1109/3DIMPVT.2011.43].

Sampling relevant points for surface registration

Rodolà, Emanuele;
2011

Abstract

Surface registration is a fundamental step in the reconstruction of three-dimensional objects. This is typically a two-step process where an initial coarse motion estimation is followed by a refinement step that almost invariably is some variant of Iterative Closest Point (ICP), which iteratively minimizes a distance function measured between pairs of selected neighboring points. The selection of relevant points on one surface to match against points on the other surface is an important issue in any efficient implementation of ICP, with strong implications both on the convergence speed and on the quality of the final alignment. This is due to the fact that typically on a surface there are a lot of low-curvature points that scarcely constrain the rigid transformation and an order of magnitude less descriptive points that are more relevant for finding the correct alignment. This results in a tendency of surfaces to "overfit" noise on low-curvature areas sliding away from the correct alignment. In this paper we propose a novel relevant-point sampling approach for ICP based on the idea that points in an area of great change constrain the transformation more and thus should be sampled with higher frequency. Experimental evaluations confront the alignment accuracy obtained with the proposed approach with those obtained with the commonly adopted uniform subsampling and normal-space sampling strategies. © 2011 IEEE.
2011
2011 International Conference on 3D Imaging, Modeling, Processing, Visualization and Transmission, 3DIMPVT 2011
alignment; imaging systems; motion estimation
04 Pubblicazione in atti di convegno::04b Atto di convegno in volume
Sampling relevant points for surface registration / Torsello, Andrea; Rodolà, Emanuele; Albarelli, Andrea. - (2011), pp. 290-295. (Intervento presentato al convegno 2011 International Conference on 3D Imaging, Modeling, Processing, Visualization and Transmission, 3DIMPVT 2011 tenutosi a Hangzhou; China) [10.1109/3DIMPVT.2011.43].
File allegati a questo prodotto
File Dimensione Formato  
Torsello_Sampling_2011.pdf

solo gestori archivio

Tipologia: Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 2.42 MB
Formato Adobe PDF
2.42 MB Adobe PDF   Contatta l'autore

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/11573/1227693
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 25
  • ???jsp.display-item.citation.isi??? ND
social impact