Photorealistic image color style transfer compression

Abstract

Existing digital image color style transfer encoding methods are often forced to compromise between performing artifact-free local image processing and performing sufficiently expressive global image processing. Moreover, such existing image style encoding methods may be under-constrained (thereby producing more visible artifacts in stylized output images than would be desired) or over-constrained (and thereby not being expressive enough to sufficiently learn and reproduce local/spatial color changes in the stylized output images). Thus, disclosed herein are techniques to combine the advantageous aspects of existing image stylization methods in a novel hybrid image processing method that effectively bifurcates the learning and reproduction of pixel luminance changes from the learning and reproduction of pixel color changes in stylized output images. Such techniques may also advantageously capture local color changes without introducing excessive compression artifacts in the generated stylized output images—while still performing the color style transfer image processing operations in a computationally-efficient fashion.