Adaptive pixel/patch-based synthesis for texture compression

This paper presents an adaptive scheme for synthesizing missing textured regions. In synthesis-based compression approaches, large textures are removed at encoder side and filled in at decoder side. This work proposes a synthesizer in which both complementary pixel-based and patch-based approaches are used. According to results shown by synthesis algorithms, patch-based and pixel-based approaches are efficient with different kinds of texture. Two algorithms are adapted to the region synthesis context: the sample patch is built from surrounding texture and potential anchor blocks inside the removed region; the scan order depends on a confidence map in order to take advantage of the designed patch; DCT-descriptors provide the minimum size of matching window which is a required parameter for both synthesizers. Finally an "a posteriori" gradient based assessor enables the synthesizer to switch between algorithms.