FluidRain is a lightweight video deraining model that leverages a divergence‑free rain flow field to guide Loop‑in‑Loop attention across scales and neighboring frames, eliminating the need for explicit motion alignment. By projecting estimated rain‑flow onto a divergence‑free subspace, the method steers window attention along rain streaks, enabling efficient temporal aggregation with only 0.80 M parameters. Experiments on four benchmarks demonstrate competitive performance against larger models, and the authors introduce a new RainSyn‑Gust dataset and a physics‑based no‑reference metric for evaluating real‑rain removal.
By Pu Wang, Yongcong Wang, Wenhao Li, Xiang Chen, Guangwei Gao, Jinshan Pan, Siyuan Yao, Shujun Fu, Zhuoran Zheng
arXiv:2606. 00281v1 Announce Type: cross Abstract: Generative machine learning is an increasingly important complement to dynamical downscaling for producing high-resolution precipitation projections, with diffusion models currently the leading approach.
By Tom Wetherell
arXiv:2512. 17897v2 Announce Type: replace-cross Abstract: We present RadarGen, a diffusion model for synthesizing realistic automotive radar point clouds from multi-view camera imagery.
By Tomer Borreda, Fangqiang Ding, Sanja Fidler, Shengyu Huang, Or Litany
arXiv:2609.38926v1 Announce Type: cross
Abstract: Long-term precipitation nowcasting requires modeling radar-echo evolution while preserving localized high-intensity structures. Recent radar-specific...
By Yufeng Zhu, Dan Niu, Qiliang Wu, Weiwei Huang, Yixiao Liang, Yongchao Feng, Chunlei Shi
arXiv:2608. 03822v1 Announce Type: cross Abstract: Developing robust flood assessment models requires high-quality paired satellite imagery, yet such data remain scarce for flood-specific image generation.
By Zhang Weihui, Wang Ruizhi, Xu Hongye, Wang Huiqiong, Sun Li, Song Mingli
arXiv:2608.30205v1 Announce Type: new
Abstract: Localized extreme precipitation is a major trigger of urban flash floods and landslides, yet producing nowcasts that combine fine spatial detail with p...
By Dohyun Park, Changhoon Song, Tengyuan Chang, Yoo-Geun Ham, Youngjoon Hong
arXiv:2607. 12171v1 Announce Type: cross Abstract: In rectified-flow-based generative models, the neural network can be trained to predict two different targets, such as the instantaneous velocity or the data endpoint, to perform denoising.
By Xu Han, Jiajing Hu, Li-Ping Liu
arXiv:2605. 13181v2 Announce Type: replace-cross Abstract: Precipitation nowcasting remains challenging due to the highly localized, rapidly evolving, and heterogeneous nature of atmospheric dynamics.
By Penghui Wen, Zexin Hu, Sen Zhang, Patrick Filippi, Xiaogang Zhu, Allen Benter, Thomas Bishop, Zhiyong Wang, Kun Hu
arXiv:2608. 16546v1 Announce Type: cross Abstract: Most super-resolution models learn from paired data by supervising only the final high-resolution output.
By Zikang Zhan
arXiv:2607. 26645v1 Announce Type: cross Abstract: Existing point-based generative methods for outdoor scenes primarily focus on LiDAR-conditioned completion.
By Wenzhe He, Meng Wang, JiaWei Qian, Jinfeng Xu, Ying Liu, Ruihui Li
Developing robust flood assessment models requires high-quality paired satellite imagery, yet such data remain scarce for flood-specific image generation. Although generative models provide a promising means of data augmentation, existing methods often yield implausible spatial layouts of flooded regions and distort scene structures.
DiFF is a generative framework that uses Doppler velocity cues from 4D millimeter-wave radar to improve human motion flow estimation. It combines Doppler-informed motion priors with a Kolmogorov‑Arnold Network (KAN) based conditional flow matching model, featuring a KAN‑attention mechanism for expressive feature extraction. Experiments demonstrate that DiFF achieves state‑of‑the‑art performance, reducing 3D endpoint error to the millimeter scale on the mmBody benchmark.
By Kai Wang, Mingle Zhao