A new compression-based image composition strategy on sort-last parallel rendering system

The cluster computer based parallel rendering is an effective method to build applications with better performance and higher resolution. Compression-based image composition is the key component of sort-last parallel rendering system. In this paper, we propose a set of strategies for compression-based image composition on sort-last parallel rendering system. Our strategy consists of three algorithms: A template-based LZW lossless compression method and a depth-buffer interpolation method to deal with the depth information of the images; A JPEG-based chromatic information compression method; and a composition method based on alpha blending. The experimental results show that our strategy is more effective than traditional compression based image composition strategies when used on sort-last parallel rendering system.