Accurately reconstructing the 3D structure of tornadoes is critically important for understanding and preparing for this highly destructive weather phenomenon. While modern 3D scene reconstruction techniques, such as 3D Gaussian splatting (3DGS), could provide a valuable tool for reconstructing the 3D structure of tornados, at present we are critically lacking a controlled tornado dataset with which to develop and validate these tools. In this work we capture and release a novel multiview dataset of a small lab-based tornado. We demonstrate one can effectively reconstruct and visualize the 3D structure of this tornado using 3DGS.
@article{arxiv.2506.18677,
title = {Reconstructing Tornadoes in 3D with Gaussian Splatting},
author = {Adam Yang and Nadula Kadawedduwa and Tianfu Wang and Sunny Sharma and Emily F. Wisinski and Jhayron S. Pérez-Carrasquilla and Kyle J. C. Hall and Dean Calhoun and Jonathan Starfeldt and Timothy P. Canty and Maria Molina and Christopher Metzler},
journal= {arXiv preprint arXiv:2506.18677},
year = {2025}
}