Compression and Rendering of Textured Point Clouds via Sparse Coding

dc.contributor.authorSchuster, Kerstenen_US
dc.contributor.authorTrettner, Philipen_US
dc.contributor.authorSchmitz, Patricen_US
dc.contributor.authorSchakib, Julianen_US
dc.contributor.authorKobbelt, Leifen_US
dc.contributor.editorBinder, Nikolaus and Ritschel, Tobiasen_US
dc.date.accessioned2021-07-05T07:48:00Z
dc.date.available2021-07-05T07:48:00Z
dc.date.issued2021
dc.description.abstractSplat-based rendering techniques produce highly realistic renderings from 3D scan data without prior mesh generation. Mapping high-resolution photographs to the splat primitives enables detailed reproduction of surface appearance. However, in many cases these massive datasets do not fit into GPU memory. In this paper, we present a compression and rendering method that is designed for large textured point cloud datasets. Our goal is to achieve compression ratios that outperform generic texture compression algorithms, while still retaining the ability to efficiently render without prior decompression. To achieve this, we resample the input textures by projecting them onto the splats and create a fixed-size representation that can be approximated by a sparse dictionary coding scheme. Each splat has a variable number of codeword indices and associated weights, which define the final texture as a linear combination during rendering. For further reduction of the memory footprint, we compress geometric attributes by careful clustering and quantization of local neighborhoods. Our approach reduces the memory requirements of textured point clouds by one order of magnitude, while retaining the possibility to efficiently render the compressed data.en_US
dc.description.sectionheadersCompression
dc.description.seriesinformationHigh-Performance Graphics - Symposium Papers
dc.identifier.doi10.2312/hpg.20211284
dc.identifier.isbn978-3-03868-156-4
dc.identifier.issn2079-8687
dc.identifier.pages61-73
dc.identifier.urihttps://doi.org/10.2312/hpg.20211284
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/hpg20211284
dc.publisherThe Eurographics Associationen_US
dc.subjectComputing methodologies
dc.subjectPoint based models
dc.subjectTexturing
dc.subjectImage compression
dc.titleCompression and Rendering of Textured Point Clouds via Sparse Codingen_US
Files
Original bundle
Now showing 1 - 2 of 2
Loading...
Thumbnail Image
Name:
061-073.pdf
Size:
49.48 MB
Format:
Adobe Portable Document Format
No Thumbnail Available
Name:
images.zip
Size:
330.87 MB
Format:
Zip file