Guardado en:
Detalles Bibliográficos
Autores principales: Yang, Adam, Kadawedduwa, Nadula, Wang, Tianfu, Sharma, Sunny, Wisinski, Emily F., Pérez-Carrasquilla, Jhayron S., Hall, Kyle J. C., Calhoun, Dean, Starfeldt, Jonathan, Canty, Timothy P., Molina, Maria, Metzler, Christopher
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2506.18677
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912565335949312
author Yang, Adam
Kadawedduwa, Nadula
Wang, Tianfu
Sharma, Sunny
Wisinski, Emily F.
Pérez-Carrasquilla, Jhayron S.
Hall, Kyle J. C.
Calhoun, Dean
Starfeldt, Jonathan
Canty, Timothy P.
Molina, Maria
Metzler, Christopher
author_facet Yang, Adam
Kadawedduwa, Nadula
Wang, Tianfu
Sharma, Sunny
Wisinski, Emily F.
Pérez-Carrasquilla, Jhayron S.
Hall, Kyle J. C.
Calhoun, Dean
Starfeldt, Jonathan
Canty, Timothy P.
Molina, Maria
Metzler, Christopher
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_18677
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Reconstructing Tornadoes in 3D with Gaussian Splatting
Yang, Adam
Kadawedduwa, Nadula
Wang, Tianfu
Sharma, Sunny
Wisinski, Emily F.
Pérez-Carrasquilla, Jhayron S.
Hall, Kyle J. C.
Calhoun, Dean
Starfeldt, Jonathan
Canty, Timothy P.
Molina, Maria
Metzler, Christopher
Computer Vision and Pattern Recognition
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.
title Reconstructing Tornadoes in 3D with Gaussian Splatting
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.18677