To what extent can three-dimensional shape and radiance be inferred from a collection of images? Can the two be estimated separately while retaining optimality? How should the opt...
We propose a new fast facial-feature extraction technique for embedded face-recognition applications. A deformable feature model is adopted, of which the parameters are optimized t...
Most illuminant estimation algorithms worked on point light sources or directional light sources. Little attempt has been made, however, to estimate area light sources. In this pa...
We describe a new variational lower-bound on the minimum energy configuration of a planar binary Markov Random Field (MRF). Our method is based on adding auxiliary nodes to every...
Julian Yarkony, Alexander T. Ihler, Charless C. Fo...
In the last few years, new view synthesis has emerged as an important application of 3D stereo reconstruction. While the quality of stereo has improved, it is still imperfect, and...
Samuel W. Hasinoff, Sing Bing Kang, Richard Szelis...