GRAPH-BASED LIFTING TRANSFORM FOR INTRA-PREDICTED VIDEO CODING

In this paper, we propose a graph-based lifting transform for intra-predicted video sequences. The transform can approximate the performance of a Graph Fourier Transform (GFT) for a given graph, but does not require computing eigenvectors. A predict-update bipartition is designed based on a Gaussian Markov Random Field (GMRF) model with the goal to minimize the energy in the prediction set. Additionally, a novel re-connection method is applied for multi-level graphs, leading to significant gain for the proposed bipartition method and for the conventional MaxCut based bipartition. Experiments on intra-predicted video sequences show that the proposed method, even considering the extra overhead for edge information, outperforms the Discrete Cosine Transform (DCT) and approximates the performance of the higher complexity GFT.