• Corpus ID: 195886591

City-GAN: Learning architectural styles using a custom Conditional GAN architecture

@article{Bachl2019CityGANLA,
  title={City-GAN: Learning architectural styles using a custom Conditional GAN architecture},
  author={Maximilian Bachl and Daniel C. Ferreira},
  journal={ArXiv},
  year={2019},
  volume={abs/1907.05280}
}
Generative Adversarial Networks (GANs) are a well-known technique that is trained on samples (e.g. pictures of fruits) and which after training is able to generate realistic new samples. Conditional GANs (CGANs) additionally provide label information for subclasses (e.g. apple, orange, pear) which enables the GAN to learn more easily and increase the quality of its output samples. We use GANs to learn architectural features of major cities and to generate images of buildings which do not exist… 
Re-designing cities with conditional adversarial networks
TLDR
This research opens the door for machine intelligence to play a role in re-thinking and re-designing the different attributes of cities based on adversarial learning, going beyond the mainstream of facial landmarks manipulation or image synthesis from semantic segmentation.
Exploring in the Latent Space of Design: A Method of Plausible Building Facades Images Generation, Properties Control and Model Explanation Base on StyleGAN2
  • Sheng Meng
  • Computer Science
    Proceedings of the 2021 DigitalFUTURES
  • 2021
TLDR
By implementing StyleGAN2 model, plausible building façade images could be generated without conditional input and by applying GANSpace to analysis the latent space, high-level properties could be controlled for both generated images and novel images outside of training set.
Automated Urban Planning for Reimagining City Configuration via Adversarial Learning: Quantification, Generation, and Evaluation
TLDR
An adversarial learning framework is developed, in which a generator takes the surrounding context representations as input to generate a land-use configuration, and a discriminator learns to distinguish between positive and negative samples.
A Review of AI and AI Intelligence Assessment
TLDR
This paper comprehensively review the current studies on AI systems, and concludes that these studies could be classified into two groups, i.e. the design as well as development of AI systems and the intelligence assessment of AI.

References

SHOWING 1-7 OF 7 REFERENCES
Conditional generative adversarial nets for convolutional face generation
TLDR
An extension of generative adversarial networks (GANs) to a conditional setting is applied, and the likelihood of real-world faces under the generative model is evaluated, and how to deterministically control face attributes is examined.
Conditional Generative Adversarial Nets
TLDR
The conditional version of generative adversarial nets is introduced, which can be constructed by simply feeding the data, y, to the generator and discriminator, and it is shown that this model can generate MNIST digits conditioned on class labels.
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
TLDR
This work introduces a class of CNNs called deep convolutional generative adversarial networks (DCGANs), that have certain architectural constraints, and demonstrates that they are a strong candidate for unsupervised learning.
Generic 3D Representation via Pose Estimation and Matching
TLDR
This paper empirically shows that the internal representation of a multi-task ConvNet trained to solve the above core problems generalizes to novel 3D tasks without the need for fine-tuning and shows traits of abstraction abilities.
Generative Adversarial Networks. arXiv:1406.2661 [cs, stat
  • (June 2014). http://arxiv.org/abs/1406
  • 2014
Deep Convolution Generative Adversarial Networks
  • 2019
Generative Adversarial Networks
  • 2018