Abstract. We propose a new method for face recognition under arbitrary pose and illumination conditions, which requires only one training image per subject. Furthermore, no limitat...
Looking around in our every day environment, many of the encountered objects are specular to some degree. Actively using this fact when reconstructing objects from image sequences...
Movies segmentation into semantically correlated units is a quite tedious task due to ”semantic gap”. Low-level features do not provide useful information about the semantical...
In this paper, we address the problem of shadow detection and removal from single images of natural scenes. Different from traditional methods that explore pixel or edge informati...
Block-based motion and disparity compensation are popular techniques to exploit correlation between video frames. Block sizes used for compensation can be chosen to achieve a good...
Jae Hoon Kim, Antonio Ortega, Peng Yin, Purvin Pan...