Composite Classifier-Free Guidance for Multi-Modal Conditioning in Wind Dynamics Super-Resolution
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915678106157056 |
|---|---|
| author | Schnell, Jacob Makkar, Aditya Gani, Gunadi Ashok, Aniket Srinivasan Lo, Darren Optis, Mike Wong, Alexander Chen, Yuhao |
| author_facet | Schnell, Jacob Makkar, Aditya Gani, Gunadi Ashok, Aniket Srinivasan Lo, Darren Optis, Mike Wong, Alexander Chen, Yuhao |
| contents | Various weather modelling problems (e.g., weather forecasting, optimizing turbine placements, etc.) require ample access to high-resolution, highly accurate wind data. Acquiring such high-resolution wind data, however, remains a challenging and expensive endeavour. Traditional reconstruction approaches are typically either cost-effective or accurate, but not both. Deep learning methods, including diffusion models, have been proposed to resolve this trade-off by leveraging advances in natural image super-resolution. Wind data, however, is distinct from natural images, and wind super-resolvers often use upwards of 10 input channels, significantly more than the usual 3-channel RGB inputs in natural images. To better leverage a large number of conditioning variables in diffusion models, we present a generalization of classifier-free guidance (CFG) to multiple conditioning inputs. Our novel composite classifier-free guidance (CCFG) can be dropped into any pre-trained diffusion model trained with standard CFG dropout. We demonstrate that CCFG outputs are higher-fidelity than those from CFG on wind super-resolution tasks. We present WindDM, a diffusion model trained for industrial-scale wind dynamics reconstruction and leveraging CCFG. WindDM achieves state-of-the-art reconstruction quality among deep learning models and costs up to $1000\times$ less than classical methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_13729 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Composite Classifier-Free Guidance for Multi-Modal Conditioning in Wind Dynamics Super-Resolution Schnell, Jacob Makkar, Aditya Gani, Gunadi Ashok, Aniket Srinivasan Lo, Darren Optis, Mike Wong, Alexander Chen, Yuhao Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition Various weather modelling problems (e.g., weather forecasting, optimizing turbine placements, etc.) require ample access to high-resolution, highly accurate wind data. Acquiring such high-resolution wind data, however, remains a challenging and expensive endeavour. Traditional reconstruction approaches are typically either cost-effective or accurate, but not both. Deep learning methods, including diffusion models, have been proposed to resolve this trade-off by leveraging advances in natural image super-resolution. Wind data, however, is distinct from natural images, and wind super-resolvers often use upwards of 10 input channels, significantly more than the usual 3-channel RGB inputs in natural images. To better leverage a large number of conditioning variables in diffusion models, we present a generalization of classifier-free guidance (CFG) to multiple conditioning inputs. Our novel composite classifier-free guidance (CCFG) can be dropped into any pre-trained diffusion model trained with standard CFG dropout. We demonstrate that CCFG outputs are higher-fidelity than those from CFG on wind super-resolution tasks. We present WindDM, a diffusion model trained for industrial-scale wind dynamics reconstruction and leveraging CCFG. WindDM achieves state-of-the-art reconstruction quality among deep learning models and costs up to $1000\times$ less than classical methods. |
| title | Composite Classifier-Free Guidance for Multi-Modal Conditioning in Wind Dynamics Super-Resolution |
| topic | Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.13729 |