Multiscale Online Dictionary Learning for Quality Scalable Video Coding

This paper proposes a novel multiscale online dictionary learning algorithm with double sparsity structure for scalable video coding. Along hierarchical structures on the feature set by wavelet transform, the search space of online learning is optimized to sub-blocks for hierarchical sparsity. The group sparsity is exploited on lowest sub-band in the base layer to obtain the low-frequency sub-dictionary and sparse coefficient. We also designed cross-scale decomposition and reconstruction, for which the recovery error can be bounded. The dictionary is updated by stochastic gradient descent to optimize the expected cost. Hierarchical high-frequency information is predicted from a pre-learned corresponding sub-dictionary pairs for scalable coding. We demonstrated that the proposed algorithm can achieve scalable signal to noise ratio (SNR). Given a video sequence Fh with group of pictures (GOP), it is decomposed into a selected HR key frames XH and the down-sampled LR non-key frames ZL. Through a standard codec, XH and ZL are coded and decoded. At the receiver, the multi-scale dictionary will be learned from HR key frames for each wavelet level. The HR version X̂Hl would be recovered from ẐL by the scalable super-resolution reconstruction via sparse representation in a SNR-scalable manner. The multiscale super-resolution reconstruction can be defined as an energy minimization: f (αdL,XH) = arg min X,Hlα