The development of the infrastructure for ubiquitous computing is progressing rapidly, yet the applications that will be built on this new infrastructure remain largely ill define...
We present a framework for accelerating interactive rendering, grounded in psychophysical models of visual perception. This framework is applicable to multiresolution rendering te...
It is well-known that the eigenvalue spectrum of the Laplacian matrix of a network contains valuable information about the network structure and the behavior of many dynamical proc...
Victor M. Preciado, Michael M. Zavlanos, Ali Jadba...
—Light occlusions are one of the most significant difficulties of photometric stereo methods. When three or more images are available without occlusion, the local surface orien...
In recent years, gradient-based LSTM recurrent neural networks (RNNs) solved many previously RNN-unlearnable tasks. Sometimes, however, gradient information is of little use for t...