Abstract: Neural networks of suitable topology are trained with sets of images, where one image of each set depicts a garment and another pair of images of each set depicts an item of apparel from multiple viewpoints, and a final image of each set depicts a model wearing the garment and the other item of apparel. Once trained, the neural network can synthesize a new image based on input images including an image of a garment and a pair of images of another item of apparel. Quantitative parameters controlling the image synthesis permit adjustment of features of the synthetic image, including skin tone, body shape and pose of the model, as well as characteristics of the garment and other items of apparel.

Abstract: Neural networks of suitable topology are trained with sets of images, where one image of each set depicts a garment and another pair of images of each set depicts an item of apparel from multiple viewpoints, and a final image of each set depicts a model wearing the garment and the other item of apparel. Once trained, the neural network can synthesize a new image based on input images including an image of a garment and a pair of images of another item of apparel. Quantitative parameters controlling the image synthesis permit adjustment of features of the synthetic image, including skin tone, body shape and pose of the model, as well as characteristics of the garment and other items of apparel.

Abstract: A subject's head position and motion can be tracked by analyzing a series of frames from a monocular camera and mapping distinguishing points visible in the frames onto an elliptical cylinder. The tracking data can be used to control a physical pan/tilt actuator or to reconfigure/reposition virtual objects, images of which can be synthesized and displayed, or composited back into the original frames and displayed.

Abstract: Neural networks of suitable topology are trained with pairs of images, where one image of each pair depicts a garment, and the other image of each pair depicts the garment being worn by a model. Once trained, the neural network can synthesize an image based on a new image of a garment, where the synthesized image could plausibly have appeared in the training set, paired with the new image of the garment. Quantitative parameters controlling the image synthesis permit adjustment of features of the synthetic image, including the skin tone, body shape and pose of the model, accessories depicted in the synthetic image, and characteristics of the garment as depicted, such as length, sleeve style, collar style or tightness.

Abstract: Neural networks of suitable topology are trained with pairs of images, where one image of each pair depicts a garment, and the other image of each pair depicts the garment being worn by a model. Once trained, the neural network can synthesize an image based on a new image of a garment, where the synthesized image could plausibly have appeared in the training set, paired with the new image of the garment. Quantitative parameters controlling the image synthesis permit adjustment of features of the synthetic image, including the skin tone, body shape and pose of the model, accessories depicted in the synthetic image, and characteristics of the garment as depicted, such as length, sleeve style, collar style or tightness.

Abstract: A subject's head position and motion can be tracked by analyzing a series of frames from a monocular camera and mapping distinguishing points visible in the frames onto an elliptical cylinder. The tracking data can be used to control a physical pan/tilt actuator or to reconfigure/reposition virtual objects, images of which can be synthesized and displayed, or composited back into the original frames and displayed.