245 papers with code • 30 benchmarks • 21 datasets
Image-to-image translation is the task of taking images from one domain and transforming them so they have the style (or characteristics) of images from another domain.
Controllable person image generation aims to produce realistic human images with desirable attributes (e. g., the given pose, cloth textures or hair style).
We provide the code of MSG U-Net model at https://github. com/laxmaniron/MSG-U-Net.
Existing image-to-image translation (I2IT) methods are either constrained to low-resolution images or long inference time due to their heavy computational burden on the convolution of high-resolution feature maps.
Ranked #1 on Photo Retouching on MIT-Adobe 5k (480p)
Unpaired image-to-image translation using Generative Adversarial Networks (GAN) is successful in converting images among multiple domains.
We introduce a new architecture called a conditional invertible neural network (cINN), and use it to address the task of diverse image-to-image translation for natural images.
Unsupervised image-to-image translation tasks aim to find a mapping between a source domain X and a target domain Y from unpaired training data.
In this paper, we explore the 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.
Ranked #1 on Sketch-to-Image Translation on Scribble
Experimental results on the CMU-Panoptic dataset demonstrate the effectiveness of the suggested framework in generating photo-realistic images of persons with new poses that are more consistent across all views in comparison to a standard Image-to-Image baseline.