Abstract: A three-dimensional structure acquisition method is provided, wherein the three-dimensional structure acquisition method includes: an input step for inputting images from a camera to a computer; a first extraction step for extracting a three-dimensional structure from the images by a predetermined method; a generation step for generating depth maps from the three-dimensional structure; a calibration step for correcting image deviation due to camera fluctuation by using the depth maps; a second extraction step for extracting a three-dimensional structure from the calibrated images by the predetermined method; and an outputting step for outputting the three-dimensional structure to a storage device. The predetermined method may be based on epipolar plane image analysis.

Abstract: Data containing the shape and motion of an object, the eye point and similar data is input to generate animation image data. For all frames, the motion of each image point is computed through utilization of data on the motion of the object and eye point used for producing the animation and, on the basis of the computed motion of the image point, spatio-temporal filtering is performed for anti-aliasing.