• Corpus ID: 238407831

ClimateGAN: Raising Climate Change Awareness by Generating Images of Floods

@article{Schmidt2022ClimateGANRC,
  title={ClimateGAN: Raising Climate Change Awareness by Generating Images of Floods},
  author={Victor Schmidt and Alexandra Sasha Luccioni and M'elisande Teng and Tianyu Zhang and Alexia Reynaud and Sunand Raghupathi and Gautier Cosne and Adrien Juraver and V. T. Vardanyan and Alex Hern{\'a}ndez-Garc{\'i}a and Yoshua Bengio},
  journal={ArXiv},
  year={2022},
  volume={abs/2110.02871}
}
Climate change is a major threat to humanity, and the actions required to prevent its catastrophic consequences include changes in both policy-making and individual behaviour. However, taking action requires understanding the effects of climate change, even though they may seem abstract and distant. Projecting the potential consequences of extreme climate events such as flooding in familiar places can help make the abstract impacts of climate change more concrete and encourage action. As part… 

SURFGenerator: Generative Adversarial Network Modeling for Synthetic Flooding Video Generation

This work proposes a novel generative adversarial network (GAN)-based Synthetic Urban Recurrent Flooding (SURF) generator for generating synthetic videos of flooding at different water depth levels and generates synthetic flooding videos with physically relevant features such as moving ripples and small waves when cars move on the flooded streets.

An Architecture for the detection of GAN-generated Flood Images with Localization Capabilities

It is found that adding a localization branch helps the network to focus on the most relevant image regions with significant improvements in terms of generalization capabilities and robustness against image processing operations.

Creativity and Machine Learning: A Survey

An overview of the history and the state of the art of computational creativity theories, key machine learning techniques (including generative deep learning), and corresponding automatic evaluation methods is presented.

ClimateNeRF: Physically-based Neural Rendering for Extreme Climate Synthesis

Physical simulations produce excellent predictions of weather effects. Neural radiance fields produce SOTA scene models. We describe a novel NeRF-editing procedure that can fuse physical simulations

References

SHOWING 1-10 OF 37 REFERENCES

Flood depth mapping in street photos with image processing and deep neural networks

The Cityscapes Dataset for Semantic Urban Scene Understanding

This work introduces Cityscapes, a benchmark suite and large-scale dataset to train and test approaches for pixel-level and instance-level semantic labeling, and exceeds previous attempts in terms of dataset size, annotation richness, scene variability, and complexity.

Communicating Local Climate Risks Online Through an Interactive Data Visualization

Findings revealed strong effects—regardless of geographic proximity—for interacting with the website on participants’ perceived reality of climate change, attitude certainty, and concern for climate change.

Weather GAN: Multi-Domain Weather Translation Using Generative Adversarial Networks

A multi-domain weather translation approach based on generative adversarial networks (GAN), denoted as Weather GAN, which can achieve the transferring of weather conditions among sunny, cloudy, foggy, rainy and snowy.

Future Coastal Population Growth and Exposure to Sea-Level Rise and Coastal Flooding - A Global Assessment

This work combines spatially explicit estimates of the baseline population with demographic data in order to derive scenario-driven projections of coastal population development and highlights countries and regions with a high degree of exposure to coastal flooding and help identifying regions where policies and adaptive planning for building resilient coastal communities are not only desirable but essential.

Adversarial Text-to-Image Synthesis: A Review

The Mapillary Vistas Dataset for Semantic Understanding of Street Scenes

The Mapillary Vistas Dataset is a novel, large-scale street-level image dataset containing 25000 high-resolution images annotated into 66 object categories with additional, instance-specific labels for 37 classes, aiming to significantly further the development of state-of-the-art methods for visual road-scene understanding.