No abstract

No abstract

High-dynamic range (HDR) images are commonly used in computer graphics for accurate rendering. However, it is inefficient to store these images because of their large data size. Although vector quantization approach can be used to compress them, a large number of representative colors are still needed to preserve acceptable image quality. This paper presents an efficient color quantization approach to compress HDR images. In the proposed approach, a 1D/2D neighborhood structure is defined for the self-organizing map (SOM) approach and the SOM approach is then used to train a color palette. Afterward, a virtual color palette that has more codevectors is simulated by interpolating the trained color palette. The interpolation process is hardware supported in the current graphics hardware. Hence, there is no need to store the virtual color palette as the representative colors are constructed on the fly. Experimental results show that our approach can obtain good image quality with a moderate color palette.Keywords Self-organizing map (SOM) Á Color quantization Á High-dynamic range (HDR) Á Large color palette virtualization (LCPV)

Vector quantization (VQ) is an effective technique applicable in a wide range of areas, such as image compression and pattern recognition. The most time-consuming procedure of VQ is codebook training, and two of the frequently used training algorithms are LBG and selforganizing map (SOM). Nowadays, desktop computers are usually equipped with programmable graphics processing units (GPUs), whose parallel data-processing ability is ideal for codebook training acceleration. Although there are some GPU algorithms for LBG training, their implementations suffer from a large amount of data transfer between CPU and GPU and a large number of rendering passes within a training iteration. This paper presents a novel GPU-based training implementation for LBG and SOM training. More specifically, we utilize the random write ability of vertex shader to reduce the overheads mentioned above. Our experimental results show that our approach can run four times faster than the previous approach.

No abstract