William T. Freeman
نویسندگان
چکیده
Image intensity variations can result from several di erent object surface e ects, including shading from 3-dimensional relief of the object, or paint on the surface itself. An essential problem in vision, which people solve naturally, is to attribute the proper physical cause, e.g. surface relief or paint, to an observed image. We addressed this problem with an approach combining psychophysical and Bayesian computational methods. We assessed human performance on a set of test images, and found that people made fairly consistent judgements of surface properties. Our computational model assigned simple prior probabilities to di erent relief or paint explanations for an image, and solved for the most probable interpretation in a Bayesian framework. The ratings of the test images by our algorithm compared surprisingly well with the mean ratings of our subjects. To appear in: Neural Information Processing Systems 10, 1998.
منابع مشابه
Learning Local Evidence for Shading and Reflectance
A fundamental, unsolved vision problem is to distinguish image intensity variations caused by surface normal variations from those caused by re ectance changes{ie, to tell shading from paint. A solution to this problem is necessary for machines to interpret images as people do and could have many
متن کاملEstimating the Material Properties of Fabric Through the Observation of Motion
We present a framework for predicting the physical properties of moving deformable objects observed in video. We apply our framework to analyze videos of fabrics moving under various unknown wind forces, and recover two key material properties of the fabric: stiffness and mass. We extend features previously developed to compactly represent static image textures to describe video textures such a...
متن کامل