Fujitsu Corporation

Kabushiki Kaisha Toshiba

Telecommunications Advancement Organization of Japan

Hiroshi Harashima

Kazuya Kodama

Robert Hsu

Akira Nakagawa

Takahiro Saito

Akihiro Yamori

Eishi Morimatsu

Kazuo Ohzeki

Masahide Kaneko

A processing of causing a face image of a person A as an object of encoding to be deformed in correspondence to expression and motion of a face image of a person B as a reference image. The expression change and the motion from the model wire-frame are treated as fitting information, and this fitting information is made WA1 with respect to a first image of an object for photographing, while is made Wb1 with respect to a second image of an object for photographing. For example, the fitting information from a model wire-frame W00 to an image A1 is Wa1, and the fitting information from the image A1 to the model wire-frame W00 is Wa1. Next, an image A2 into which the first image A1 is caused to be deformed by a texture Ta1 of the first image A1 and a wire-frame function Wb1 Wa1 is obtained through composition. Texture mapping of sticking the texture Ta1 in correspondence to each of small areas of this wire-frame is carried out, whereby the image A2 into which the image A1 is caused to be deformed similarly to an image B1 is obtained through composition.

Model-based coding/decoding method and system

An image generation apparatus is provided with an image acquisition unit for acquiring images of a three-dimensional object from a plurality of positions along a curve by computer graphics or a television camera. A memory unit stores images obtained by the image acquisition unit. An address generating unit calculates a first address showing the position of the image acquisition and a second address showing the position corresponding to the direction of the line of sight in the image according to the first address, for each line of sight from a specified viewpoint according to the positional information for the viewpoint and the curve at the time of image acquisition. An image generation processing unit combines the image information read from the memory unit by the first and second addresses generated by the address generating unit and generates the image of the three-dimensional object. Display equipment displays the image.

System for generating image of three-dimensional object seen from

A system for processing 3-D multiple-view images which can render an image of a 3-D object as seen from any arbitrary viewpoint based on the 3-D multiple-view images, provided with an image acquisition unit for acquiring 3-D multiple-view images of a 3-D object as seen from a plurality of viewpoints, an image analysis unit for analyzing 3-D multiple-view images comprised of a plurality of images and finding the layered feature trajectory information comprised of trajectories linking identical points of the 3-D object, an image interpolation unit for rendering by interpolation an image of the 3-D object as seen from a specified (by user) viewpoint based on the layered feature trajectory information, an image compression unit for approximating the shape and color and texture information for the individual trajectories of the layered feature trajectory information for compression coding, a memory unit for storing the coded layered feature trajectory information, and an image reconstruction unit for reconstructing the coded layered feature trajectory information read from the memory unit to the original layered feature trajectory information and applying it to the image interpolation unit.

Method and apparatus for processing 3-D multiple view images formed of a

Growing community of inventors

Tokyo, Japan

Hiroshi Harashima