Abstract: There is provided a method of processing image data, comprising the steps of: (a) providing a plurality of images of a scene; (b) generating a disparity map for each of at least two pairs of images from the plurality of images; (c) transforming each of the disparity maps into a common coordinate system; and (d) merging the transformed disparity maps to provide a single representation of the depth information of the scene.

Abstract: There is provided a method and apparatus for processing images to create a novel view of a scene. The method comprises the steps of: (a) providing first and second images of a scene; (b) applying a stereo matching algorithm to the first and second images to generate a first disparity map which maps between corresponding points from the first image to the second image; (c) forward mapping the first disparity map into the coordinates of a third image to generate a second disparity map; (d) using the second disparity map, reverse mapping for at least some of the pixel positions in the third image to corresponding points in the first and second images to obtain possible color values for each of the at least some of the pixels in the third image; and (e) assigning a final color value to each of the at least some of the pixels in the third image on the basis of the possible color values, thereby providing a novel view of the scene.

Abstract: A method of processing data is privided. The method comprises the steps of: comparing first and second samples of a space, the first and second samples being related by a set of transformations, to provide a set of pairs of signals, each of said pairs of signals corresponding to substantially the same feature in the space in the first and second samples; for each of the pairs of signals, evaluating residuals corresponding to the differences between the values of the space in each sample; evaluating a first estimate of the set of transformations from the residuals; estimating a tensor field representing orientation of flow in the space, the tensor field covering at least one point in the space; and recalculating, from the first estimate and the tensor field, the residuals for each of the pairs of signals to improve the estimate of the set of transformations.

Abstract: There is provided a method of processing image data, comprising the steps of: (a) providing a plurality of images of a scene; (b) generating a disparity map for each of at least two pairs of images from the plurality of images; (c) transforming each of the disparity maps into a common coordinate system; and (d) merging the transformed disparity maps to provide a single representation of the depth information of the scene.

Abstract: There is provided a method and apparatus for processing images to create a novel view of a scene. The method comprises the steps of: (a) providing first and second images of a scene; (b) applying a stereo matching algorithm to the first and second images to generate a first disparity map which maps between corresponding points from the first image to the second image; (c) forward mapping the first disparity map into the coordinates of a third image to generate a second disparity map; (d) using the second disparity map, reverse mapping for at least some of the pixel positions in the third image to corresponding points in the first and second images to obtain possible colour values for each of the at least some of the pixels in the third image; and (e) assigning a final colour value to each of the at least some of the pixels in the third image on the basis of the possible colour values, thereby providing a novel view of the scene.

Abstract: A method of processing data is provided. The method comprises the steps of: comparing first and second samples of a space, the first and second samples being related by a set of transformations, to provide a set of pairs of signals, each of the pairs of signals corresponding to substantially the same feature in the space in the first and second samples; for each of the pairs of signals, evaluating residuals corresponding to the differences between the values of the space in each sample; evaluating a first estimate of the set of transformations from the residuals; estimating a tensor field representing orientation of flow in the space, the tensor field covering at least one point in the space; and recalculating, from the first estimate and the tensor field, the residuals for each of the pairs of signals to improve the estimate of the set of transformations.