Data compression on the illumination adjustable images by PCA and ICA

Abstract

In the image-based relighting (IBL), tremendous reference images are needed to provide a high quality rendering. Therefore, a data compression is a must for its real applications. In this paper, two global analysis methods, the principal component analysis (PCA) and the independent component analysis (ICA), are used to compress the huge IBL data by exploiting its correlation properties. Both approaches approximate the raw data with a small number of global base images, and they follow a similar algorithm structure: base images extraction, raw data representation, and further compression on the base images and the representing coefficients. What differs is that PCA only removes the second-order data correlation, but ICA reduces nearly all order statistics data dependence, which should benefit the data compression. Simulations are given to evaluate their performance. Comparisons are also made between them and JPEG2000 and MPEG. The evaluation results show that both approaches are superior to JPEG2000 and MPEG. Although ICA tends to remove higher order dependence than PCA, it is a little inferior to PCA in terms of compression ratio/reconstruction error performance.