Surface Dependent Representations for Illumination Insensitive Image Comparison
IEEE Transactions on Pattern Analysis and Machine Intelligence
Using specularities in comparing 3D models and 2D images
Computer Vision and Image Understanding
Image-based lighting adjustment method for browsing object images
ICME'09 Proceedings of the 2009 IEEE international conference on Multimedia and Expo
Specularity removal in images and videos: a PDE approach
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part I
Camera and light calibration from reflections on a sphere
Computer Vision and Image Understanding
Hi-index | 0.00 |
Recognition systems have generally treated specular highlightsas noise. We show how to use these highlights asa positive source of information that improves recognitionof shiny objects. This also enables us to recognize verychallenging shiny transparent objects, such as wine glasses.Specifically, we show how to find highlights that are consistentwith an hypothesized pose of an object of known 3Dshape. We do this using only a qualitative description ofhighlight formation that is consistent with most models ofspecular reflection, so no specific knowledge of an object'sreflectance properties is needed. We first present a methodthat finds highlights produced by a dominant compact lightsource, whose position is roughly known. We then show howto estimate the lighting automatically for objects whose reflectionis part specular and part Lambertian. We demonstratethis method for two classes of objects. First, we showthat specular information alone can suffice to identify objectswith no Lambertian reflectance, such as transparentwine glasses. Second, we use our complete system to recognizeshiny objects, such as pottery.