Recent approaches to learning structured predictors often require approximate inference for tractability; yet its effects on the learned model are unclear. Meanwhile, most learnin...
We present a self-calibrating photometric stereo method. From a set of images taken from a fixed viewpoint under different and unknown lighting conditions, our method automaticall...
Many people do not read easily. They may have an impairment such as a visual problem. They may be reading in stressful conditions or poor light, or perhaps they are reading in a s...
Partially preordered belief bases are very convenient for an efficient representation of incomplete knowledge. They offer flexibility and avoid to compare unrelated pieces of inf...
We study the mathematical and numerical aspects of the estimation of the 3-D shape of a Lambertian scene seen under diffuse illumination. This problem is known as “shape from amb...