Image-based methods of representation and rendering of three-dimensional object and animated three-dimensional object

Abstract

Provided are three-dimensional still and animated object representations obtained from photos of real-life objects and their geometrical representations, allowing compact storage, fast rendering with high output image quality, suitable for animation purposes. The method includes transforming original data of a three-dimensional object into an intermediate representation; transforming data of the intermediate representation into a rendering representation in the form of a circumscribing cube, where a layered depth image is attributed to each face of the circumscribing cube, and rendering the obtained representation by determining visible faces of the circumscribing cube with account of the viewer's position, transforming the layered depth image for each of the visible faces into a texture, and visualizing the visible faces with texture.