Progressive Splatting of Continuous Scatterplots and Parallel Coordinates

dc.contributor.authorHeinrich, Julianen_US
dc.contributor.authorBachthaler, S.en_US
dc.contributor.authorWeiskopf, Danielen_US
dc.contributor.editorH. Hauser, H. Pfister, and J. J. van Wijken_US
dc.date.accessioned2014-02-21T20:23:18Z
dc.date.available2014-02-21T20:23:18Z
dc.date.issued2011en_US
dc.description.abstractContinuous scatterplots and parallel coordinates are used to visualize multivariate data defined on a continuous domain. With the existing techniques, rendering such plots becomes prohibitively slow, especially for large scientific datasets. This paper presents a scalable and progressive rendering algorithm for continuous data plots that allows exploratory analysis of large datasets at interactive framerates. The algorithm employs splatting to produce a series of plots that are combined using alpha blending to achieve a progressively improving image. For each individual frame, splats are obtained by transforming Gaussian density kernels from the 3-D domain of the input dataset to the respective data domain. A closed-form analytic description of the resulting splat footprints is derived to allow pre-computation of splat textures for efficient GPU rendering. The plotting method is versatile because it supports arbitrary reconstruction or interpolation schemes for the input data and the splatting technique is scalable because it chooses splat samples independently from the size of the input dataset. Finally, the effectiveness of the method is compared to existing techniques regarding rendering performance and quality.en_US
dc.description.number3en_US
dc.description.seriesinformationComputer Graphics Forumen_US
dc.description.volume30en_US
dc.identifier.doi10.1111/j.1467-8659.2011.01914.xen_US
dc.identifier.issn1467-8659en_US
dc.identifier.urihttps://doi.org/10.1111/j.1467-8659.2011.01914.xen_US
dc.publisherThe Eurographics Association and Blackwell Publishing Ltd.en_US
dc.subjectProbability and Statistics [G.3]en_US
dc.subjectMultivariate Statisticsen_US
dc.subjectComputer Graphics [I.3.3]en_US
dc.subjectPicture/Image Generationen_US
dc.subjectDisplay algorithmsen_US
dc.titleProgressive Splatting of Continuous Scatterplots and Parallel Coordinatesen_US
Files