<?xml version="1.0" encoding="ISO-8859-1"?>
<metadatalist>
	<metadata ReferenceType="Conference Proceedings">
		<identifier>6qtX3pFwXQZeBBx/w4kh2</identifier>
		<repository>sid.inpe.br/banon/2002/11.04.11.11</repository>
		<metadatarepository>sid.inpe.br/banon/2002/11.04.11.11.14</metadatarepository>
		<site>sibgrapi.sid.inpe.br 802</site>
		<citationkey>Torrećo:2000:ShShIn</citationkey>
		<author>Torrećo, José R. A.,</author>
		<title>Shape from shading and intensity gradient</title>
		<conferencename>Brazilian Symposium on Computer Graphics and Image Processing, 13 (SIBGRAPI)</conferencename>
		<year>2000</year>
		<editor>Carvalho, Paulo Cezar Pinto,</editor>
		<editor>Walter, Marcelo,</editor>
		<date>October</date>
		<publisheraddress>Los Alamitos</publisheraddress>
		<publisher>IEEE Computer Society</publisher>
		<conferencelocation>Gramado, RS, Brazil</conferencelocation>
		<keywords>computer vision, shape from shading, intensity gradient, shape estimation, brightness gradient, Green function approach, shape-from-shading, GSFS, single brightness image, uniform disparity field, matching image, linear expansion, reflectance map, surface gradient, closed-form depth map, free parameters, parameter estimation, depth estimate, higher-frequency components, imaged surface, real images, computer vision technique.</keywords>
		<abstract>We present a novel algorithm for shape estimation, using both brightness and brightness gradient as input data. Our algorithm is an improvement of the recently introduced Green's function approach to shape-from-shading (GSFS). In GSFS, we assume that the single brightness image will be matched to a second image through a uniform disparity field, and solve for the matching image via Green's function. When a linear expansion of the reflectance map is considered, the matching image can be related to surface gradient, leading to a closed-form depth map whose free parameters are easily estimated. The author shows that the same procedure can be repeated with the gradient image as input; a second depth estimate thus results which takes into account higher-frequency components of the imaged surface. Extensive experimentation with synthetic and real images corroborates the advantage of the new method.</abstract>
		<notes>The conference was held in Gramado, RS, Brazil, from October 17 to 20.</notes>
		<organization>SBC - Brazilian Computer Society</organization>
		<tertiarytype>Full Paper</tertiarytype>
		<size>689 KiB</size>
		<numberoffiles>1</numberoffiles>
		<targetfile>7-14.pdf</targetfile>
		<lastupdate>2002:11.04.02.00.00 sid.inpe.br/banon/2001/03.30.15.38 administrator</lastupdate>
		<metadatalastupdate>2020:02.19.02.58.51 sid.inpe.br/banon/2001/03.30.15.38 administrator {D 2000}</metadatalastupdate>
		<usergroup>administrator</usergroup>
		<visibility>shown</visibility>
		<transferableflag>1</transferableflag>
		<hostcollection>sid.inpe.br/banon/2001/03.30.15.38</hostcollection>
		<contenttype>External Contribution</contenttype>
		<lasthostcollection>sid.inpe.br/banon/2001/03.30.15.38</lasthostcollection>
		<url>http://sibgrapi.sid.inpe.br/rep-/sid.inpe.br/banon/2002/11.04.11.11</url>
	</metadata>
</metadatalist>