We address the texture level-of-detail problem for extremely large surfaces such as terrain during realtime, view-dependent rendering. A novel texture hierarchy is introduced base...
Synthetic images can be parameterized by more than time or viewpoint. We generalize image-based rendering by exploiting texture-mapping graphics hardware to decompress ray-traced ...
Ziyad S. Hakura, Jerome Edward Lengyel, John M. Sn...
Recent studies have shown that machine learning can improve the accuracy of detecting object boundaries in images. In the standard approach, a boundary detector is trained by mini...
Viren Jain, Benjamin Bollmann, Bobby Kasthuri, Ken...
Visual dictionaries are widely employed in object recognition to map unordered bags of local region descriptors into feature vectors for image classification. Most visual dictiona...
We propose to bridge the gap between Random Field (RF) formulations for joint categorization and segmentation (JCaS), which model local interactions among pixels and superpixels, ...