Learning Bilinear Models for Two-Factor Problems in Vision
|MERL Report: ||TR96-37: W. T. Freeman, J. B. Tenenbaum
Proc. IEEE Computer Vision and Pattern Recognition (CVPR '97), Puerto Rico
In many vision problems, we want to infer two (or more) hidden factors which interact to produce our observations. We may want to disentangle illuminant and object colors in color constancy; rendering conditions from surface shape in shape-from-shading; face identity and head pose in face recognition; or font and letter class in character recognition. We refer to these two factors generically as "style" and "content". This paper received Outstanding Paper prize, CVPR '97.