PHENOM: Interest Points on Photometric Normal Maps

dc.contributor.authorSabzevari, Rezaen_US
dc.contributor.authorAlak, Erenen_US
dc.contributor.authorScaramuzza, Davideen_US
dc.contributor.editorB. Solenthaler and E. Puppoen_US
dc.date.accessioned2015-04-15T18:40:51Z
dc.date.available2015-04-15T18:40:51Z
dc.date.issued2015en_US
dc.description.abstractThis paper introduces a novel method for extracting features and matching points on images of texture-less surfaces. Feature points are extracted from surface normal maps recovered by Photometric Stereo. Such sparse matching will help to register high detail 3D surfaces reconstructed from multiple view images. Moreover, the geometric constraints imposed by multiple views can be utilized to correct the geometric ambiguity in photometric reconstruction. Experiments show the performance of proposed interest points in matching texture-less objects. Comparison against texture-based interest points shows that the proposed features based on normal maps perform effectively.en_US
dc.description.sectionheadersPostersen_US
dc.description.seriesinformationEG 2015 - Postersen_US
dc.identifier.doi10.2312/egp.20151040en_US
dc.identifier.pages19-20en_US
dc.identifier.urihttps://doi.org/10.2312/egp.20151040en_US
dc.publisherThe Eurographics Associationen_US
dc.subjectI.4.8 [Image Processing and Computer Vision]en_US
dc.subjectScene Analysisen_US
dc.subjectPhotometryen_US
dc.subjectI.4.5 [Image Processing and Computer Vision]en_US
dc.subjectReconstructionen_US
dc.subjectTransform methodsen_US
dc.titlePHENOM: Interest Points on Photometric Normal Mapsen_US
Files