Direction-Adaptive Transforms for Coding Prediction Residuals

In this paper, we present 2-D direction-adaptive transforms for coding prediction residuals of video. These Direction-Adaptive Residual Transforms (DART) are shown to be more effective than the traditional 2-D DCT when coding residual blocks that contain directional features. After presenting the directional transform structures and improvements to their efficiency, we outline how they are used to code both Inter and Intra prediction residuals. For Intra coding, we also demonstrate the relation between the prediction mode and the optimal DART orientation. Experimental results exhibit up to 7% and 9.3% improvements in compression efficiency in JM 16.0 and JM-KTA 2.6r1 respectively, as compared to using only the conventional H.264/AVC transform.