h3dema/GANs

Brief collection of Generative Adversarial Networks bibliography

Generative Adversarial Networks

This is a brief collection of GAN bibliography, with papers, tutorials and links to code.

Papers and tutorials

• NIPS 2016 Tutorial about GAN by Goodfellow.
• Video from Goodfellow's NIPS 2016 tutorial.
• First paper on "Generative Adversarial Networks" by Ian J. Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, Yoshua Bengio. ArXiv 2014.
• WU, Jiajun et al. Learning a probabilistic latent space of object shapes via 3d generative-adversarial modeling. In: Advances in neural information processing systems. 2016. p. 82-90.
• CHANG, Angel X. et al. Shapenet: An information-rich 3d model repository. arXiv preprint arXiv:1512.03012, 2015.
• CHOY, Christopher B. et al. 3d-r2n2: A unified approach for single and multi-view 3d object reconstruction. In: European conference on computer vision. Springer, Cham, 2016. p. 628-644.
• KALOGERAKIS, Evangelos et al. A probabilistic model for component-based shape synthesis. ACM Transactions on Graphics (TOG), v. 31, n. 4, p. 1-11, 2012.
• FISHER, Matthew et al. Example-based synthesis of 3D object arrangements. ACM Transactions on Graphics (TOG), v. 31, n. 6, p. 1-11, 2012.
• AVERKIOU, Melinos et al. Shapesynth: Parameterizing model collections for coupled shape exploration and synthesis. In: Computer Graphics Forum. 2014. p. 125-134.
• DENTON, Emily L. et al. Deep generative image models using a laplacian pyramid of adversarial networks. In: Advances in neural information processing systems. 2015. p. 1486-1494.
• NASH, Charlie; WILLIAMS, Christopher KI. The shape variational autoencoder: A deep generative model of part‐segmented 3D objects. In: Computer Graphics Forum. 2017. p. 1-12.
• RADFORD, Alec; METZ, Luke; CHINTALA, Soumith. Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv preprint arXiv:1511.06434, 2015.
• YUMER, Mehmet Ersin et al. Procedural modeling using autoencoder networks. In: Proceedings of the 28th Annual ACM Symposium on User Interface Software & Technology. 2015. p. 109-118.
• Least squares generative adversarial networks
• Self-attention generative adversarial networks.
• Unrolled) generative adversarial networks.
• Coupled generative adversarial networks.
• Stackgan: Text to photo-realistic image synthesis with stacked generative adversarial networks

GANs with Reinforcement Learning

• Pfau, D. and Vinyals, O. (2016). Connecting generative adversarial networks and actor-critic methods. arXiv preprint arXiv:1610.01945.

• Finn, C., Christiano, P., Abbeel, P., and Levine, S. (2016a). A connection between generative adversarial networks, inverse reinforcement learning, and energy-based models. arXiv preprint arXiv:1611.03852.

• Ho, J. and Ermon, S. (2016). Generative adversarial imitation learning. In Advances in Neural Information Processing Systems, pages 4565{4573)

Web pages

• Nice introduction to GAN with code.

Talks and videos

• Ian Goodfellow talk to Lex Fridman in his podcast.
• Ian Goodfellow talking about Adversarial Machine Learning in ICLR 2019.

Tricks

• Tricks by Chintala et al. presented in NIPS 2016 on how to train a GAN.

Code

• My repository forked from Erik Linder-Norén's and ported to Python 3 and Jupyter
• Tensorflow implementation of DCGAN. The referenced torch code can be found here.
• SR-GAN Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network implemented in Keras
• Code and hyperparameters for the paper orginal GAN from Goodfellow et al.
• Unrolled GAN in Keras.