21 datasets found

Generating artistic portraits is a challenging problem in computer vision. Existing portrait stylization models that generate good quality results are based on Image-to-Image...

100STYLE dataset is used to train the style motion prompt for the topology-shifted stylization diffusion model.

MotionS uses two public datasets, namely BABEL and 100STYLE, to train its cross-modality style embedding and topology-shifted stylization diffusion model.

The dataset used in this paper is a style-guided generation task with Stable Diffusion. The dataset contains images with different styles and prompts.

We build two explainable style transfer datasets by augmenting existing datasets with synthetic textual explanations generated by a teacher model.

We build two explainable style transfer datasets by augmenting existing datasets with synthetic textual explanations generated by a teacher model.

We build two explainable style transfer datasets by augmenting existing datasets with synthetic textual explanations generated by a teacher model.

A dataset of paired style and content images used for customizing a pre-trained text-to-image model with a single image pair.

LocalStyleFool: Regional Video Style Transfer Attack Using Segment Anything

The dataset used in the paper is a large collection of small images, each representing a patch of a jigsaw puzzle. The patches are of the same size and orientation, and the goal...

The dataset used in the paper is Morpho-MNIST, which contains 60,000 images each of "normal" and "transformed" digits, which are drawn with a thinner and thicker stroke.

A custom dataset created for this paper, consisting of 2107 point clouds, each with 16384 points, and three design point clouds: stripes, porous, and cut.

Photorealism is a complex concept that cannot easily be formulated mathematically. Deep Photo Style Transfer is an attempt to transfer the style of a reference image to a...

The dataset used in the paper for text-to-image generation and style transfer tasks.

The dataset proposed by Xia et al. (2015) contains six content classes and eight different styles for each type of motion.

The dataset used for artistic style transfer tasks, including artwork-artwork, photo-to-artwork, and artwork-to-photo.

A font transfer dataset with 26 capital letters of size 64x64.

Motions are from two publicly available datasets: Xia et al. [Xia et al. 2015] and HumanAct12 [Guo et al. 2020].

Large scale datasets [18, 17, 27, 6] boosted text conditional image generation quality. However, in some domains it could be difficult to make such datasets and usually it could...

The Cityscapes dataset is a large and famous city street scene semantic segmentation dataset. 19 classes of which 30 classes of this dataset are considered for training and...