Our primary contribution is the addition of recurrent connections to the network in order to drastically improve temporal stability for sequences of sparsely sampled input images. We allow for much larger pixel neighborhoods to be taken into account, while also improving execution speed by an order of magnitude. Motivated by recent advances in image restoration with deep convolutional networks, we propose a variant of these networks better suited to the class of noise present in Monte Carlo rendering. Our primary focus is on reconstruction of global illumination with extremely low sampling budgets at interactive rates.
Quote We describe a machine learning technique for reconstructing image sequences rendered using Monte Carlo methods.
0 kommentar(er)
