Rate-Distortion Evaluation for Two-Layer Coding Systems

The Bjontegaard model is widely used to calculate the compression efficiency between different codecs. However, this model is not sufficient to investigate the impact on quality of the interaction of the base and enhancement layer bit rates when comparing two-layer coding systems. Therefore, in this paper, we propose an extension of the Bjontegaard model from rate-distortion (R-D) curve fitting to rate-rate-distortion (R^2-D) surface fitting. The proposed model uses a cubic surface as fitting function and a more complex characterization of the domain formed by the data points to compute a more realistic estimate of compression efficiency. The proposed model can be used to measure the compression efficiency of two-layer coding systems, as well as for other applications, e.g., to optimize the bit rate allocation between texture and depth in 3D video coding. Two examples of assessment of compression efficiency in JPEG XT are presented as illustrations.