thumbnail

Fast Low-Memory Seamless Photo Blending on Massive Point Clouds using a Streaming Framework

Ruggero Pintus, Enrico Gobbetti, and Marco Callieri

2011

Abstract

We present an efficient scalable streaming technique for mapping highly detailed color information on extremely dense point clouds. Our method does not require meshing or extensive processing of the input model, works on a coarsely spatially-reordered point stream and can adaptively refine point cloud geometry on the basis of image content. Seamless multi-band image blending is obtained by using GPU accelerated screen-space operators, which solve point set visibility, compute a per-pixel view-dependent weight and ensure a smooth weighting function over each input image. The proposed approach works independently on each image in a memory coherent manner, and can be easily extended to include further image quality estimators. The effectiveness of the method is demonstrated on a series of massive real-world point datasets.

Reference and download information

Ruggero Pintus, Enrico Gobbetti, and Marco Callieri. Fast Low-Memory Seamless Photo Blending on Massive Point Clouds using a Streaming Framework. ACM Journal on Computing and Cultural Heritage, 4(2): Article 6, 2011.

Related multimedia productions

Bibtex citation record

@Article{Pintus:2011:FLS,
    author = {Ruggero Pintus and Enrico Gobbetti and Marco Callieri},
    title = {Fast Low-Memory Seamless Photo Blending on Massive Point Clouds using a Streaming Framework},
    journal = {ACM Journal on Computing and Cultural Heritage},
    volume = {4},
    number = {2},
    pages = {Article 6},
    year = {2011},
    abstract = { We present an efficient scalable streaming technique for mapping highly detailed color information on extremely dense point clouds. Our method does not require meshing or extensive processing of the input model, works on a coarsely spatially-reordered point stream and can adaptively refine point cloud geometry on the basis of image content. Seamless multi-band image blending is obtained by using GPU accelerated screen-space operators, which solve point set visibility, compute a per-pixel view-dependent weight and ensure a smooth weighting function over each input image. The proposed approach works independently on each image in a memory coherent manner, and can be easily extended to include further image quality estimators. The effectiveness of the method is demonstrated on a series of massive real-world point datasets. },
    url = {http://vic.crs4.it/vic/cgi-bin/bib-page.cgi?id='Pintus:2011:FLS'},
}