Abstract: A method is described which included receiving (S1) a number of object images (IMn) of an object (1). Each object image (IMn) corresponds to a different view direction (n). The object images include first (IM1) and second (IM2) object images corresponding to first (n1) and second (n2) directions. The method also includes determining (S2) a mesh (20) corresponding to the target region (5) of the object (1) surface (2) based on a first subset (MESH) of the number of object images (IMn) which includes two or more object images (IMn) of the number of object images (IMn). The method also includes determining (S3) diffuse (DFUV) and specular (SPUV) maps corresponding to the target region (5) of the object (1) surface (2) based on processing a second subset (REFLECT) of the object images (IMn) using a deep learning neural network model trained to estimate diffuse (DFn) and specular (SPn) albedo components based on an input image (IMn).

Abstract: A method for performing interactive operation upon a stereoscopic image and a stereoscopic image display system are provided. The stereoscopic image display system includes a stereoscopic display and a gesture sensor. In the method, the stereoscopic display displays the stereoscopic image, and the gesture sensor senses a gesture. A current gesture state is obtained. A previous state of the stereoscopic image and a previous gesture state are obtained. Stereo coordinate variations corresponding to the gesture can be calculated according to the current gesture state and the previous gesture state. New stereoscopic image data can be obtained according to the previous state of the stereoscopic image and the stereo coordinate variations corresponding to the gesture. The stereoscopic display is used to display a new stereoscopic image that is rendered from the new stereoscopic image data.

Abstract: A method for performing interactive operation upon a stereoscopic image and a stereoscopic image display system are provided. The stereoscopic image display system includes a stereoscopic display and a gesture sensor. In the method, the stereoscopic display displays the stereoscopic image, and the gesture sensor senses a gesture. A current gesture state is obtained. A previous state of the stereoscopic image and a previous gesture state are obtained. Stereo coordinate variations corresponding to the gesture can be calculated according to the current gesture state and the previous gesture state. New stereoscopic image data can be obtained according to the previous state of the stereoscopic image and the stereo coordinate variations corresponding to the gesture. The stereoscopic display is used to display a new stereoscopic image that is rendered from the new stereoscopic image data.