DC Field | Value | Language |
---|---|---|
dc.contributor.author | Klose, F. | ko |
dc.contributor.author | Wang, O. | ko |
dc.contributor.author | Bazin, J. C. | ko |
dc.contributor.author | Magnor, M. | ko |
dc.contributor.author | Sorkine-Hornung, A. | ko |
dc.date.accessioned | 2017-09-08T05:34:42Z | - |
dc.date.available | 2017-09-08T05:34:42Z | - |
dc.date.created | 2017-09-04 | - |
dc.date.created | 2017-09-04 | - |
dc.date.issued | 2015-10-07 | - |
dc.identifier.citation | 20th International Symposium on Vision, Modeling and Visualization, VMV 2015, pp.103 - 110 | - |
dc.identifier.uri | http://hdl.handle.net/10203/225739 | - |
dc.description.abstract | We describe a method to efficiently collect and filter a large set of 2D pixel observations of unstructured 3D points, with applications to scene-space aware video processing. One of the main challenges in scene-space video processing is to achieve reasonable computation time despite the very large volumes of data, often in the order of billions of pixels. The bottleneck is determining a suitable set of candidate samples used to compute each output video pixel color. These samples are observations of the same 3D point, and must be gathered from a large number of candidate pixels, by volumetric 3D queries in scene-space. Our approach takes advantage of the spatial and temporal continuity inherent to video to greatly reduce the candidate set of samples by solving 3D volumetric queries directly on a series of 2D projections, using out-of-core data streaming and an efficient GPU producerconsumer scheme that maximizes hardware utilization by exploiting memory locality. Our system is capable of processing over a trillion pixel samples, enabling various scene-space video processing applications on full HD video output with hundreds of frames and processing times in the order of a few minutes. | - |
dc.language | English | - |
dc.publisher | Eurographics Association | - |
dc.title | Efficient GPU based sampling for scene-space video processing | - |
dc.type | Conference | - |
dc.identifier.scopusid | 2-s2.0-85018305771 | - |
dc.type.rims | CONF | - |
dc.citation.beginningpage | 103 | - |
dc.citation.endingpage | 110 | - |
dc.citation.publicationname | 20th International Symposium on Vision, Modeling and Visualization, VMV 2015 | - |
dc.identifier.conferencecountry | GE | - |
dc.identifier.conferencelocation | RWTH Aachen University | - |
dc.identifier.doi | 10.2312/vmv.20151264 | - |
dc.contributor.localauthor | Bazin, J. C. | - |
dc.contributor.nonIdAuthor | Klose, F. | - |
dc.contributor.nonIdAuthor | Wang, O. | - |
dc.contributor.nonIdAuthor | Magnor, M. | - |
dc.contributor.nonIdAuthor | Sorkine-Hornung, A. | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.