We describe how to model the appearance of a 3-D object using multiple views, learn such a model from training images, and use the model for object recognition. The model uses pro...
Establishing correspondences between two feature sets is a fundamental issue in computer vision, pattern recognition, and machine learning. This problem can be well formulated as g...
Jungmin Lee (Seoul National University), Minsu Cho...
This paper proposes contour-based features for articulated pose estimation. Most of recent methods are designed using tree-structured models with appearance evaluation only within...
We show that we can effectively and automatically fit a complex facial animation model to uncalibrated image sequences. Our approach is based on model-driven bundleadjustment foll...
We present a novel directionally adaptive image interpolation based on a multiple-direction wavelet transform, called directionlets. The algorithm uses directionlets to efficient...