FrancescoCoding/ArtGAN

ArtGAN: This work presents a series of new approaches to improve Generative Adversarial Network (GAN) for conditional image synthesis and we name the proposed model as “ArtGAN”. Implementations are in Caffe/Tensorflow.

ArtGAN Code Release

Updated on May 18, 2018 (Improved ArtGan models are included)

Updated on May 15, 2018 (merge ArtGAN implementation)

Released on December 20, 2016

Description

This consists of the implementations of our:

• TIP-19 work with titled Improved ArtGAN for Conditional Synthesis of Natural Image and Artwork. The preliminary version of this work was presented earlier in ICIP-17 with titled ArtGAN: Artwork Synthesis with Conditional Categorial GANs. Please refer to the ArtGAN folder.

• ICIP-16 work with titled Ceci n'est pas une pipe: A Deep Convolutional Network for Fine-art Paintings Classification. Please refer to the ICIP-16 folder.

Feedback

Suggestions and opinions of this work (both positive and negative) are greatly welcome. Please contact the authors by sending email to wrtan.edu at gmail.comor cs.chan at um.edu.my.

License

The project is open source under BSD-3 license (see the LICENSE file). Codes can be used freely only for academic purpose.

For commercial purpose usage, please contact Dr. Chee Seng Chan at cs.chan at um.edu.my