9223803 Hodges An animation sequence may be thought of as a series of images (frames) sampled from a continuously changing scene. The temporal sampling rate is high, 24-30 frames per second, so that any particular frame is usually very similar to the frame that preceded and succeeded it. This similarity is known as frame-to- frame or temporal coherence. The majority of computer graphics images are generated as part of a sequence of animation frames. The usual approach for producing these images, however, is to render each frame in an animation as if it were a single, isolated image. The purpose of this research is to develop faster algorithms for the generation of animated sequences of ray-traced images by exploiting temporal coherence. The idea here is that the information gained when ray-tracing a particular frame in a sequence may be used to speed up the ray-tracing of other nearby frames. the goal of this project is the development of efficient algorithms to infer the pixel values of one or more animation frames from a ray-traced reference frame. The reference frame may have been fully ray-traced or contain a combination of ray- traced and inferred pixel values. ***