A GPU favor representation method for plenoptic-illumination function based on an efficient spherical partition scheme
Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review
Author(s)
Related Research Unit(s)
Detail(s)
Original language | English |
---|---|
Pages (from-to) | 624-636 |
Journal / Publication | Signal Processing: Image Communication |
Volume | 23 |
Issue number | 8 |
Publication status | Published - Sept 2008 |
Link(s)
Abstract
In image-based relighting (IBR), a set of reference images is pre-captured under various light directions. These reference images represent the appearance of a scene with an adjustable illumination. This paper describes a graphics process unit (GPU) favor relighting scheme for IBR. The scheme consists of two levels. In the first level, the reference images are converted into a number of lightmaps (floating point images) based on the proposing HEALPIX discrete cosine transform (HDCT). In the second level, the lightmaps are compressed with a GPU favor compression method. Novel images with complicated lighting conditions can be directly generated from those compressed lightmaps. The GPU accelerated relighting methods for the directional source and the point source are discussed. Compared with the spherical harmonic scheme and the radial basis function scheme, the proposed HDCT scheme offers the similar rendering speed and much better rendering quality. © 2008.
Research Area(s)
- HEALPIX discrete cosine transform (HDCT), Image-based rendering (IBR), Plenoptic-illumination function (PIF)
Citation Format(s)
A GPU favor representation method for plenoptic-illumination function based on an efficient spherical partition scheme. / Leung, Chi-Sing; Lam, Ping-Man; Wong, Tien-Tsin.
In: Signal Processing: Image Communication, Vol. 23, No. 8, 09.2008, p. 624-636.
In: Signal Processing: Image Communication, Vol. 23, No. 8, 09.2008, p. 624-636.
Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review