Show simple item record

dc.contributor.authorTokuyoshi, Y.en_US
dc.contributor.editorDeussen, Oliver and Zhang, Hao (Richard)en_US
dc.date.accessioned2015-10-12T13:32:46Z
dc.date.available2015-10-12T13:32:46Z
dc.date.issued2015en_US
dc.identifier.urihttp://dx.doi.org/10.1111/cgf.12525en_US
dc.description.abstractAlthough geometry‐aware filtering and upsampling have often been used for interactive or real‐time rendering, they are unsuitable for glossy surfaces because shading results strongly depend on the bidirectional reflectance distribution functions. This paper proposes a novel weighting function of cross bilateral filtering and upsampling to measure the similarity of specular lobes. The difficulty is that a specular lobe is represented with a distribution function in directional space, whereas conventional cross bilateral filtering evaluates similarities using the distance between two points in a Euclidean space. Therefore, this paper first generalizes cross bilateral filtering for the similarity of distribution functions in a non‐Euclidean space. Then, the weighting function is specialized for specular lobes. Our key insight is that the weighting function of bilateral filtering can be represented with the product integral of two distribution functions corresponding to two pixels. In addition, we propose spherical Gaussian‐based approximations to calculate this weighting function analytically. Our weighting function detects the edges of glossiness, and adapts to all‐frequency materials using only a camera position and G‐buffer. These features are not only suitable for path tracing, but also deferred shading and non‐ray tracing–based methods such as voxel cone tracing.Although geometry‐aware filtering and upsampling have often been used for interactive or real‐time rendering, they are unsuitable for glossy surfaces because shading results strongly depend on the bidirectional reflectance distribution functions. This paper proposes a novel weighting function of cross bilateral filtering and upsampling to measure the similarity of specular lobes. The difficulty is that a specular lobe is represented with a distribution function in directional space, whereas conventional cross bilateral filtering evaluates similarities using the distance between two points in a Euclidean space. Therefore, this paper first generalizes cross bilateral filtering for the similarity of distribution functions in a non‐Euclidean space. Then, the weighting function is specialized for specular lobes. Our key insight is that the weighting function of bilateral filtering can be represented with the product integral of two distribution functions corresponding to two pixels. In addition, we propose spherical Gaussian‐based approximations to calculate this weighting function analytically.en_US
dc.publisherCopyright © 2015 The Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectglobal illuminationen_US
dc.subjectimage processingen_US
dc.subjectreal‐time renderingen_US
dc.subjectI.3.3 [Computer Graphics]: Picture/Image Generationen_US
dc.titleSpecular Lobe‐Aware Filtering and Upsampling for Interactive Indirect Illuminationen_US
dc.description.seriesinformationComputer Graphics Forumen_US
dc.description.sectionheadersArticlesen_US
dc.description.volume34en_US
dc.description.number6en_US
dc.identifier.doi10.1111/cgf.12525en_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record