CRS4 Repository

Guided Robust Matte-Model Fitting for Accelerating Multi-light Reflectance Processing Techniques

Show simple item record

dc.contributor ["European Union (EU)" and "Horizon 2020"]
dc.contributor.author Pintus, Ruggero
dc.contributor.author Giachetti, Andrea
dc.contributor.author Pintore, Giovanni
dc.contributor.author Gobbetti, Enrico
dc.date.accessioned 2017-09-25T07:57:19Z
dc.date.available 2017-09-25T07:57:19Z
dc.date.issued 2017-09
dc.identifier.uri http://hdl.handle.net/1138/40
dc.identifier.uri http://www.crs4.it/vic/cgi-bin/bib-page.cgi?id=%27Pintus:2017:GRM%27
dc.description.abstract The generation of a basic matte model is at the core of many multi-light reflectance processing approaches, such as Photometric Stereo or Reflectance Transformation Imaging. To recover information on objects’ shape and appearance, the matte model is used directly or combined with specialized methods for modeling high-frequency behaviors. Multivariate robust regression offers a general solution to reliably extract the matte component when source data is heavily contaminated by shadows, inter-reflections, specularity, or noise. However, robust multivariate modeling is usually very slow. In this paper, we accelerate robust fitting by drastically reducing the number of tested candidate solutions using a guided approach. Our method propagates already known solutions to nearby pixels using a similarity-driven flood-fill strategy, and exploits this knowledge to order possible candidate solutions and to determine convergence conditions. The method has been tested on objects with a variety of reflectance behaviors, showing state-of-the-art accuracy with respect to current solutions, and a significant speed-up without accuracy reduction with respect to multivariate robust regression. en_US
dc.description.sponsorship Terms: "European Union (EU)" & "Horizon 2020" / Action: H2020-EU.3.6.3. - Reflective societies - cultural heritage and European identity / Acronym: Scan4Reco / Grant number: 665091 en_US
dc.description.sponsorship Sardinian Regional Authorities under projects VIGEC and Vis&VideoLab
dc.language.iso en en_US
dc.publisher British Machine Vision Association en_US
dc.relation info:eu-repo/grantAgreement/EC/H2020/665091/EU/Scan4Reco/Scan4Reco/
dc.rights British Machine Vision Association
dc.rights.uri info:eu-repo/semantics/openAccess
dc.source British Machine Vision Conference 2017
dc.subject Reflectance Transformation Imaging en_US
dc.subject Photometric Stereo en_US
dc.subject Robust statistics en_US
dc.subject Multivariate Robust Regression en_US
dc.subject Matte-model Fitting en_US
dc.title Guided Robust Matte-Model Fitting for Accelerating Multi-light Reflectance Processing Techniques en_US
dc.type info:eu-repo/semantics/article en_US
dc.type info:eu-repo/semantics/acceptedVersion


Files in this item

This item appears in the following Collection(s)

Show simple item record

Search DSpace


Browse

My Account