4 datasets found

The proposed framework generates JPEG compressed images using generative adversarial networks.

The CSIQ database contains 866 distorted images generated by applying 5 distortion operations at 3 ∼ 5 levels to 30 pristine images.

The proposed system is composed of three neural networks (NN): an auto-regressive module (ARM) fψ, an upsampler fυ and a synthesis fθ.

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...