Abstract: Methods and apparatus for directional texture generation using image warping. An image warping directional texture generation method may, for example, be used to design hair or hairstyles. The method may obtain one or more user strokes via a provided brush or other user interface element to paint directional texture, such as hair, onto a target image. Primitives, such as strands, wisps, partings, etc., may be used to paint the directional texture. After the user applies a stroke to paint a primitive or a portion of a primitive onto the target image, the primitive may be automatically adjusted to fit the primitive to the stroke, handle distortion artifacts, and blend the primitive into the existing image. The user may continue to apply strokes until satisfied with the overall result.

Abstract: Methods, apparatus, and computer-readable storage media for stereo drawing that enable the creation of stereoscopic image pairs. A stereo drawing system may present 3D shape(s) via a user interface (UI). The user can position and rotate a 3D shape, for example via direct manipulation technology such as motion tracking technology. A drawing surface may be mapped to an input device via which input strokes may be applied to the surface. The input strokes are mapped locally onto the surface, thereby allowing the user to draw onto a well-defined shape in 3D space. The stereo drawing system maps what is drawn onto the drawing surface; the geometry of the drawing surface provides depth information so that stereoscopic image pairs can be automatically generated.

Abstract: A method, system, and computer-readable storage medium for categorizing digital images. A plurality of semantic category scores for a digital image are determined via application of a corresponding plurality of classifiers. A semantic category profile for the image is automatically determined based on the plurality of semantic category scores, where the semantic category profile characterizes semantic content of the image, and is useable to perform semantic based operations with respect to the image.

Abstract: Methods and apparatus for directional texture generation using flow-guided, sample-based texture synthesis. A texture synthesis directional texture generation method may, for example, be used to design hair or hairstyles. The method may obtain one or more strokes, one or more optional masks, one or more optional user maps, and directional texture samples. A target region and one or more samples may be divided into patches. For each patch in the target region, a matching patch from the samples may be located according to one or more features to generate a similarity map. The patches in the target region may then be replaced with the patches from the samples according to the similarity map. To match sample patches to target region patches based on features such as color and brightness, a procedural directional texture generation method may be used as a pre-processing step.