Sequential algorithms of active learning based on the estimation of the level sets of the empirical risk are discussed in the paper. Localized Rademacher complexities are used in ...
Object detection in cluttered, natural scenes has a high
complexity since many local observations compete for object
hypotheses. Voting methods provide an efficient solution
to ...
We propose to combine a triangular element surface model with a linearized reflectance map to formulate the shape-from-shading problem. The main idea is to approximate a smooth sur...
Kyoung Mu Lee (Seoul National University), C.-C. J...
In this work, we approach the classic Mumford-Shah problem from a curve evolution perspective. In particular, we let a given family of curves define the boundaries between regions...
Given a dense set of imperfect normals obtained by photometric stereo or shape from shading, this paper presents an optimization algorithm which alternately optimizes until conver...