Re-designing cities with conditional adversarial networks
This paper introduces a conditional generative adversarial network to redesign a street-level image of urban scenes by generating 1) an urban intervention policy, 2) an attention map that localises where intervention is needed, 3) a high-resolution street-level image (1024 X 1024 or 1536 X1536) after implementing the intervention. We also introduce a new dataset that comprises aligned street-level images of before and after urban interventions from real-life scenarios that make this research possible. The introduced method has been trained on different ranges of urban interventions applied to realistic images. The trained model shows strong performance in re-modelling cities, outperforming existing methods that apply image-to-image translation in other domains that is computed in a single GPU. 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.
Code (0)
등록된 구현이 없습니다.
Tasks
Generative Adversarial NetworkGPUImage GenerationImage-to-Image TranslationSemantic SegmentationTranslationSimilar Papers 제목 키워드 기반
Deep Umbra: A Generative Approach for Sunlight Access Computation in Urban Spaces
Sunlight and shadow play critical roles in how urban spaces are utilized, thrive, and grow. While access to sunlight is essential to the success of urban environments, shadows can provide shaded places to stay during the…
Generative Adversarial NetworkCity-GAN: Learning architectural styles using a custom Conditional GAN architecture
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) addition…
RobArch: Designing Robust Architectures against Adversarial Attacks
Adversarial Training is the most effective approach for improving the robustness of Deep Neural Networks (DNNs). However, compared to the large body of research in optimizing the adversarial training process, there are f…
Designing nanophotonic structures using conditional-deep convolutional generative adversarial networks
Data-driven design approaches based on deep-learning have been introduced in nanophotonics to reduce time-consuming iterative simulations which have been a major challenge. Here, we report the first use of conditional de…
FormAttack Deterministic Conditional Image Generative Models for Diverse and Controllable Generation
Existing generative adversarial network (GAN) based conditional image generative models typically produce fixed output for the same conditional input, which is unreasonable for highly subjective tasks, such as large-mask…
Adversarial AttackConditional Image GenerationGenerative Adversarial NetworkImage Generation+2