Comparison of residual compression methods in motion compensated video

In this paper, we compare the objective performance of several algorithms for coding motion compensated residuals, including the wavelet transform, matching pursuits and an improved embedded DCT-based coding method. A motion-compensated prediction-based approach with overlapped block matching compensation (OBMC) is used in all systems in the evaluation. The results show that matching pursuits outperforms transform-based methods by 0.1-1.0 dB in PSNR. The embedded DCT coder usually outperforms the wavelet-based SPIHT-AC in the examples considered, and SPIHT is usually better than JPEG 2000.