Low-complexity adaptive multiple transforms for post-HEVC video coding

Since the introduction of the H.261 standard in 1990, the transform step has always been a key feature of video coding technologies. The successive generations of standard have always found a better way to further de-correlate the residual signals and thus improve the coding efficiency. Recently, MPEG and the ITU have jointly launched the Joint Video Exploration Team (or JVET) to prepare the next generation of video coding standard. In this context, a new approach called Adaptive Multiple Transforms (or AMT) has been introduced. Despite the provided coding efficiency, the AMT solution raises several issues especially regarding the complexity of the selected set of transforms. This can be an important issue, particularly for a future industrial adoption. In this paper, a low-complexity transform set for AMT is proposed, which aims at providing a significant reduction of the required computational power. The proposed method has been implemented in the JEM-2.0 and tested under the JVET test conditions where it provides a substantial complexity reduction of -56.5% compared to the current AMT transform set with similar R-D performance.