At the first stage, we train a network to predict a hair matte from an input hair sketch, with an optional set of non-hair strokes. Based on these observations, we present SketchHairSalon, a two-stage framework for generating realistic hair images directly from freehand sketches depicting desired hair structure and appearance. We observe that colored hair sketches already implicitly define target hair shapes as well as hair appearance and are more flexible to depict hair structures than orientation maps.
Those solutions usually encode hair structures via orientation maps, which, however, are not very effective to encode complex structures. This not only costs users extra labor but also fails to capture complicated hair boundaries. Existing solutions often require a user-provided binary mask to specify a target hair shape. Recent deep generative models allow real-time generation of hair images from sketch inputs.
0 kommentar(er)
