We propose a new family of non-submodular global energy functions that still use submodularity internally to couple edges in a graph cut. We show it is possible to develop an ef...
Many successful models for predicting attention in a scene involve three main steps: convolution with a set of filters, a center-surround mechanism and spatial pooling to constru...
Naila Murray, Maria Vanrell, Xavier Otazu, C. Alej...
Training of conditional random fields often takes the form of a double-loop procedure with message-passing inference in the inner loop. This can be very expensive, as the need to...
Blind image deconvolution is an ill-posed problem that requires regularization to solve. However, many common forms of image prior used in this setting have a major drawback in th...
Two problems occur when bundle adjustment (BA) is applied on long image sequences: the large calculation time and the drift (or error accumulation). In recent work, the calculatio...