Fast data-parallel rotation of digital volume images

Affine transformation of volume, in particular rotation, is important in visualisation. The authors present an approach to data-parallel rotation which ensures an efficient mapping from the object space to a rotated viewing space. While the popular rotation-by-shear approach involves multiple resampling, only one resampling operation is used in the algorithm which ensures faster speed and less degradation. Also, a fast rendering algorithm is proposed for the rendering of volume image. The authors implement their algorithm on a massive parallel SIMD computer Decmpp 1200/sx to show its interactivity and quality advantages.<
>