191578010 / enhancedtl Goto Github PK

DSXuq dataset: There are 18000 CG images and 18000 PG images sized from 256 × 256 to 4928× 3264 with moderate to good visual quality in
the dataset. The CG set contains traditional CG images, GAN images, and images generated by using diffusion model. 6000 traditional CG image set
were constructed by collecting CG video or game screenshots (namely Forza Horizon, GANTZ, God of War, Red Dead Redemption, and Playerunknown’s
Battlegrounds) in JPEG format from Kaggle and Google websites. We used the pretrained StyleGAN2 model and stable diffusion model to generate
6000 GAN images and 6000 DM images, respectively. For images in the PG set, 402 images with different contents were taken by the authors in Singapore using
a NIKON D5200 camera, the focal length and exposure time are 25mm and 1/200 second respectively. 1600 and 5998 images were downloaded from 
the Columbia and RAISE datasets. 10000 PG images in BOSSbase v1.01 dataset are also collected to increase the number of images.