Especially at low bit-rates current DCT-based video coding standards suffer from the disadvantage that coarse quantization and a rigid block structure result in noticeable blocking and ringing noise. In this paper we propose a spatially adaptive method for reduction of these coding artifacts based on the principle of constrained least-squares image restoration. A strictly local filter is developed which adapts to the spatial image characteristics as well as to the coding conditions. Due to the small filter kernel, the method can be applied to frame as well as object-based video coding and is also suited for quality improvement in arbitrarily shaped MPEG-4 coded video material. The proposal is numerically scalable and yields visually pleasing results for intra- as well as interframe coded images. This is also reflected by consistent PSNR improvements between 0.2 and 1.3 dB. As post-processing technique, it is compatible to all existing image and video coding standards.
展开▼
