Omni-Weather: A Unified Multimodal Model for Weather Radar Understanding and Generation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915897886638080 |
|---|---|
| author | Zhou, Zhiwang Pu, Yuandong He, Xuming Liu, Yidi Chen, Yixin Gong, Junchao Zhuang, Xiang Xu, Wanghan Cao, Qinglong Tang, Shixiang Liu, Yihao Zhang, Wenlong Bai, Lei |
| author_facet | Zhou, Zhiwang Pu, Yuandong He, Xuming Liu, Yidi Chen, Yixin Gong, Junchao Zhuang, Xiang Xu, Wanghan Cao, Qinglong Tang, Shixiang Liu, Yihao Zhang, Wenlong Bai, Lei |
| contents | Weather modeling requires both accurate prediction and mechanistic interpretation, yet existing methods treat these goals in isolation, separating generation from understanding. To address this gap, we present Omni-Weather, the first multimodal foundation model that unifies weather generation and understanding within a single architecture. Omni-Weather integrates a radar encoder for weather generation tasks, followed by unified processing using a shared self-attention mechanism. Moreover, we construct a Chain-of-Thought dataset for causal reasoning in weather generation, enabling interpretable outputs and improved perceptual quality. Extensive experiments show Omni-Weather achieves state-of-the-art performance in both weather generation and understanding. Our findings further indicate that generative and understanding tasks in the weather domain can mutually enhance each other. Omni-Weather also demonstrates the feasibility and value of unifying weather generation and understanding. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_21643 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Omni-Weather: A Unified Multimodal Model for Weather Radar Understanding and Generation Zhou, Zhiwang Pu, Yuandong He, Xuming Liu, Yidi Chen, Yixin Gong, Junchao Zhuang, Xiang Xu, Wanghan Cao, Qinglong Tang, Shixiang Liu, Yihao Zhang, Wenlong Bai, Lei Computer Vision and Pattern Recognition Weather modeling requires both accurate prediction and mechanistic interpretation, yet existing methods treat these goals in isolation, separating generation from understanding. To address this gap, we present Omni-Weather, the first multimodal foundation model that unifies weather generation and understanding within a single architecture. Omni-Weather integrates a radar encoder for weather generation tasks, followed by unified processing using a shared self-attention mechanism. Moreover, we construct a Chain-of-Thought dataset for causal reasoning in weather generation, enabling interpretable outputs and improved perceptual quality. Extensive experiments show Omni-Weather achieves state-of-the-art performance in both weather generation and understanding. Our findings further indicate that generative and understanding tasks in the weather domain can mutually enhance each other. Omni-Weather also demonstrates the feasibility and value of unifying weather generation and understanding. |
| title | Omni-Weather: A Unified Multimodal Model for Weather Radar Understanding and Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.21643 |