Improved video coding through texture analysis and synthesis

The underlying assumption of our approach is that the textures in a video scene can be labeled subjectively relevant or irrelevant. Relevant textures are defined as containing subjectively meaningful details, while irrelevant textures can be seen as image content with less important subjective details. We apply this idea to video coding using a texture analyzer and a texture synthesizer. The texture analyzer (encoder side) identifies the texture regions with unimportant subjective details and generates side information for the texture synthesizer (decoder side), which in turn inserts synthetic textures at the specified locations. In this paper, we show that bit-rate savings up to 10.2% versus a H.264/AVC codec can be achieved using a semi-automatic MPEG-7-aided texture analyzer. The subjective video quality is thereby comparable to the H.264/AVC codec without the presented approach.