Results 1 
3 of
3
Learning lowlevel vision
 International Journal of Computer Vision
, 2000
"... We show a learningbased method for lowlevel vision problems. We setup a Markov network of patches of the image and the underlying scene. A factorization approximation allows us to easily learn the parameters of the Markov network from synthetic examples of image/scene pairs, and to e ciently prop ..."
Abstract

Cited by 468 (25 self)
 Add to MetaCart
We show a learningbased method for lowlevel vision problems. We setup a Markov network of patches of the image and the underlying scene. A factorization approximation allows us to easily learn the parameters of the Markov network from synthetic examples of image/scene pairs, and to e ciently propagate image information. Monte Carlo simulations justify this approximation. We apply this to the \superresolution " problem (estimating high frequency details from a lowresolution image), showing good results. For the motion estimation problem, we show resolution of the aperture problem and llingin arising from application of the same probabilistic machinery.
Bayesian model of surface perception
 in Advances in Neural Information Processing Systems
, 1998
"... Image intensity variations can result from several different object surface effects, including shading from 3dimensional 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 ..."
Abstract

Cited by 12 (4 self)
 Add to MetaCart
Image intensity variations can result from several different object surface effects, including shading from 3dimensional 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 different 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.
Re ectance Based Object Recognition
"... Neighboring points on a smoothly curved surface have similar surface normals and illumination conditions. Therefore, their brightness values can be used to compute the ratio of their re ectance coe cients. Based on this observation, we develop an algorithm that estimates a re ectance ratio for each ..."
Abstract
 Add to MetaCart
Neighboring points on a smoothly curved surface have similar surface normals and illumination conditions. Therefore, their brightness values can be used to compute the ratio of their re ectance coe cients. Based on this observation, we develop an algorithm that estimates a re ectance ratio for each region in an image with respect to its background. The algorithm is e cient as it computes ratios for all image regions in just two raster scans. The region re ectance ratio represents a physical property thatisinvariant to illumination and imaging parameters. Several experiments are conducted to demonstrate the accuracy and robustness of ratio invariant. The ratio invariant is used to recognize objects from a single brightness image of a scene. Object models are automatically acquired and represented using a hash table. Recognition and pose estimation algorithms are presented that use ratio estimates of scene regions as well as their geometric properties to index the hash table. The result is a hypothesis for the existence of an object in the image. This hypothesis is veri ed using the ratios and locations of other regions in the scene. This approach to recognition is e ective for objects with printed characters and pictures. Recognition experiments are conducted