Region-based correspondence (RBC) is a highly relevant and non-trivial computer vision problem. Given two 3D shapes, RBC seeks segments/regions on these shapes that can be reliably put in correspondence. The problem thus consists both in finding the regions and determining the cor- respondences between them. This problem statement is sim- ilar to that of “biclustering”, implying that RBC can be cast as a biclustering problem. Here, we exploit this implication by tackling RBC via a novel biclustering approach, called S 4B (spatially smooth spike and slab biclustering), which: (i) casts the problem in a probabilistic low-rank matrix fac- torization perspective; (ii) uses a spike and slab prior to induce sparsity; (iii) is enriched with a spatial smoothness prior, based on geodesic distances, encouraging nearby vertices to belong to the same bicluster. This type of spatial prior cannot be used in classical biclustering techniques. We test the proposed approach on the FAUST dataset, out- performing both state-of-the-art RBC techniques and clas- sical biclustering methods.

Region-Based Correspondence Between 3D Shapes via Spatially Smooth Biclustering / Denitto, Matteo; Melzi, Simone; Bicego, Manuele; Castellani, Umberto; Farinelli, Alessandro; Figueiredo, Mario A. T.; Kleiman, Yanir; Ovsjanikov, Maks. - (2017), pp. 4270-4279. (Intervento presentato al convegno 16th IEEE International Conference on Computer Vision, ICCV 2017 tenutosi a Venice; Italy) [10.1109/ICCV.2017.457].

Region-Based Correspondence Between 3D Shapes via Spatially Smooth Biclustering

Melzi, Simone;Farinelli, Alessandro;
2017

Abstract

Region-based correspondence (RBC) is a highly relevant and non-trivial computer vision problem. Given two 3D shapes, RBC seeks segments/regions on these shapes that can be reliably put in correspondence. The problem thus consists both in finding the regions and determining the cor- respondences between them. This problem statement is sim- ilar to that of “biclustering”, implying that RBC can be cast as a biclustering problem. Here, we exploit this implication by tackling RBC via a novel biclustering approach, called S 4B (spatially smooth spike and slab biclustering), which: (i) casts the problem in a probabilistic low-rank matrix fac- torization perspective; (ii) uses a spike and slab prior to induce sparsity; (iii) is enriched with a spatial smoothness prior, based on geodesic distances, encouraging nearby vertices to belong to the same bicluster. This type of spatial prior cannot be used in classical biclustering techniques. We test the proposed approach on the FAUST dataset, out- performing both state-of-the-art RBC techniques and clas- sical biclustering methods.
2017
16th IEEE International Conference on Computer Vision, ICCV 2017
computer vision; pattern recognition; biclustering
04 Pubblicazione in atti di convegno::04b Atto di convegno in volume
Region-Based Correspondence Between 3D Shapes via Spatially Smooth Biclustering / Denitto, Matteo; Melzi, Simone; Bicego, Manuele; Castellani, Umberto; Farinelli, Alessandro; Figueiredo, Mario A. T.; Kleiman, Yanir; Ovsjanikov, Maks. - (2017), pp. 4270-4279. (Intervento presentato al convegno 16th IEEE International Conference on Computer Vision, ICCV 2017 tenutosi a Venice; Italy) [10.1109/ICCV.2017.457].
File allegati a questo prodotto
File Dimensione Formato  
Denitto_Region-Based_2017.pdf

solo gestori archivio

Tipologia: Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 529.64 kB
Formato Adobe PDF
529.64 kB 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/11573/1410174
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 8
  • ???jsp.display-item.citation.isi??? 5
social impact