United States Patent: 6,674,918

Inventors: Liu; Wen-Yin, Zhong; Hua, Xu; Ying-Qing

发明人：刘文印、钟华、徐迎庆

Abstract: Methods and apparatus for synthesizing images from two or more existing images are described. The described embodiment makes use of an illumination model as a mathematical model to combine the images. A first of the images is utilized as an object color or color source (i.e. the foreground) for a resultant image that is to be formed. A second of the images (utilized as the background or texture) is utilized as a perturbation source. In accordance with the described embodiment, the first image is represented by a plane that has a plurality of surface normal vectors. Aspects of the second image are utilized to perturb or adjust the surface normal vectors of the plane that represents the first image. Perturbation occurs, in the described embodiment, by determining individual intensity values for corresponding pixels of the second image. The intensity values are mapped to corresponding angular displacement values. The angular displacement values are used to angularly adjust or deviate the surface normal vectors for corresponding image pixels of the plane that represents the first image. This yields a virtual surface whose normal vectors are not fully specified, but constrained only by the angles between the original surface normal vectors and the perturbed normal vectors. In the described embodiment, after some assumptions concerning the viewing and lighting source direction, an illumination model is then applied to the virtual surface to yield a resultant synthesized image.