Adaptive anisotropic filtering (AAF) for real-time visual enhancement of MPEG-coded video sequences

Current standards for video compression achieve good performances in terms of data compaction and signal-to-noise ratio of the decoded signal. Nevertheless, there are some known problems concerning the visual quality of reconstructed images, which can be partially solved using appropriate post-processing algorithms. The paper proposes a new adaptive anisotropic filter (AAF) that aims to unify the treatment of different sources of perceptive distortion in MPEG sequences. The process is driven by a local classification of blocks and single pixels of decoded frames, taking into account several parameters (distribution of DCT coefficient energy, presence of sharp variations, spatial position of DCT block boundaries). Experimental results show that the proposed algorithm outperforms existing enhancement approaches, in particular when constraints on complexity and real-time processing are compelling.