Image "appearance" may change over time due to a variety of causes such as 1) object or camera motion; 2) generic photometric events including variations in illumination (e.g. shadows) and specular reflections; and 3) "iconic changes" which are specific to the objects being viewed and include complex occlusion events and changes in the material properties of theobjects. We propose a general framework forrepresentingand recovering these "appearance changes" in an image sequence as a "mixture" of different causes. The approach generalizes previous work on optical flowtoprovide a richer descriptionofimage events and more reliable estimates of image motion.
Michael J. Black, David J. Fleet, Yaser Yacoob