ClimateNeRF: Extreme Weather Synthesis in Neural Radiance Field

Yuan Li, Zhi-Hao Lin, David Forsyth, Jia-Bin Huang, and Shenlong Wang
International Conference on Computer Vision (ICCV), 2023

📝 Paper: https://arxiv.org/abs/2211.13226
🌐 Website: https://climatenerf.github.io/
💻 Code: https://github.com/y-u-a-n-l-i/Climate_NeRF

📄 Abstract: 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 with NeRF models of scenes, producing realistic movies of physical phenomena in those scenes. Our application -- Climate NeRF -- allows people to visualize what climate change outcomes will do to them. ClimateNeRF allows us to render realistic weather effects, including smog, snow, and flood. Results can be controlled with physically meaningful variables like water level. Qualitative and quantitative studies show that our simulated results are significantly more realistic than those from SOTA 2D image editing and SOTA 3D NeRF stylization.

Jia-Bin Huang

A research project that uses neural radiance fields (NeRF) to visualize the local impact of climate change by rendering realistic extreme weather effects — flooding, snow, smog, and wildfire smoke — into real-world scenes. The method models physically meaningful variables like water levels, snow particle density, and smog density to produce view-consistent, photorealistic simulations. Beyond climate communication, the framework can stress-test 3D object detection algorithms for autonomous vehicles under adverse weather conditions.

Visualizing Climate Change Impacts