RainDiff: End-to-end Precipitation Nowcasting Via Token-wise Attention Diffusion
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915558782402560 |
|---|---|
| author | Nguyen, Thao Ma, Jiaqi Khan, Fahad Shahbaz Taieb, Souhaib Ben Khan, Salman |
| author_facet | Nguyen, Thao Ma, Jiaqi Khan, Fahad Shahbaz Taieb, Souhaib Ben Khan, Salman |
| contents | Precipitation nowcasting, predicting future radar echo sequences from current observations, is a critical yet challenging task due to the inherently chaotic and tightly coupled spatio-temporal dynamics of the atmosphere. While recent advances in diffusion-based models attempt to capture both large-scale motion and fine-grained stochastic variability, they often suffer from scalability issues: latent-space approaches require a separately trained autoencoder, adding complexity and limiting generalization, while pixel-space approaches are computationally intensive and often omit attention mechanisms, reducing their ability to model long-range spatio-temporal dependencies. To address these limitations, we propose a Token-wise Attention integrated into not only the U-Net diffusion model but also the spatio-temporal encoder that dynamically captures multi-scale spatial interactions and temporal evolution. Unlike prior approaches, our method natively integrates attention into the architecture without incurring the high resource cost typical of pixel-space diffusion, thereby eliminating the need for separate latent modules. Our extensive experiments and visual evaluations across diverse datasets demonstrate that the proposed method significantly outperforms state-of-the-art approaches, yielding superior local fidelity, generalization, and robustness in complex precipitation forecasting scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_14962 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | RainDiff: End-to-end Precipitation Nowcasting Via Token-wise Attention Diffusion Nguyen, Thao Ma, Jiaqi Khan, Fahad Shahbaz Taieb, Souhaib Ben Khan, Salman Computer Vision and Pattern Recognition Precipitation nowcasting, predicting future radar echo sequences from current observations, is a critical yet challenging task due to the inherently chaotic and tightly coupled spatio-temporal dynamics of the atmosphere. While recent advances in diffusion-based models attempt to capture both large-scale motion and fine-grained stochastic variability, they often suffer from scalability issues: latent-space approaches require a separately trained autoencoder, adding complexity and limiting generalization, while pixel-space approaches are computationally intensive and often omit attention mechanisms, reducing their ability to model long-range spatio-temporal dependencies. To address these limitations, we propose a Token-wise Attention integrated into not only the U-Net diffusion model but also the spatio-temporal encoder that dynamically captures multi-scale spatial interactions and temporal evolution. Unlike prior approaches, our method natively integrates attention into the architecture without incurring the high resource cost typical of pixel-space diffusion, thereby eliminating the need for separate latent modules. Our extensive experiments and visual evaluations across diverse datasets demonstrate that the proposed method significantly outperforms state-of-the-art approaches, yielding superior local fidelity, generalization, and robustness in complex precipitation forecasting scenarios. |
| title | RainDiff: End-to-end Precipitation Nowcasting Via Token-wise Attention Diffusion |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2510.14962 |