9 papers with code • 3 benchmarks • 4 datasets
Previous methods directly feed the semantic layout as input to the deep network, which is then processed through stacks of convolution, normalization, and nonlinearity layers.
We present a new method for synthesizing high-resolution photo-realistic images from semantic label maps using conditional generative adversarial networks (conditional GANs).
In this paper, we explore open-domain sketch-to-photo translation, which aims to synthesize a realistic photo from a freehand sketch with its class label, even if the sketches of that class are missing in the training data.
We show that intermediate self-attention maps of a masked generative transformer encode important structural information of the input image, such as scene layout and object shape, and we propose a novel sampling method based on this observation to enable structure-guided generation.
We propose an interactive GAN-based sketch-to-image translation method that helps novice users create images of simple objects.