发表机构
Neurogica Inc.; LTS, Inc.; ME-Lab Japan, Inc.; Hokkaido University（Neurogica公司; LTS公司; ME-Lab日本公司; 北海道大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出物理引导的流图匹配（PG-FMM），通过解耦平流与随机细节，在四个雷达基准上以18/24指标领先，强降雨临界成功指数提升达58.9%。
AI 中文摘要
降水临近预报，即从过去的观测生成未来的雷达场，对于洪水预警和灾害响应至关重要。它也是时空生成建模的一个高要求基准，涉及混沌动力学、重尾强度以及最关键的罕见高强度结构。确定性模型最小化像素损失并趋向于条件均值，这恰好模糊了这些结构，而在确定性骨干之上添加随机残差的生成模型则继承了相同的模糊性。我们提出物理引导的流图匹配（PG-FMM），这是一种条件流图模型，将可预测的平流与不确定的小尺度细节解耦。一个冻结的拉格朗日平流先验传输雷达场并提供显式的运动预报，而流图生成头以过去的帧和先验滚动（而非与之相加）为条件，在四个采样步骤中产生清晰的随机细节。先验仅作为引导，因此生成头替换模糊结构而非继承它。在四个雷达基准上的大量实验表明，PG-FMM在24项指标中的18项上优于最先进的方法，在强降雨阈值上收益最大，临界成功指数最高提升58.9%。项目页面可在该https URL找到。
英文摘要
Precipitation nowcasting, generating future radar fields from past observations, is critical for flood warning and disaster response. It is also a demanding benchmark for spatiotemporal generative modeling, with chaotic dynamics, heavy-tailed intensities, and rare high-intensity structures that matter most. Deterministic models minimize a pixel loss and are driven toward the conditional mean, which blurs exactly those structures, while generative models that add a stochastic residual on top of a deterministic backbone inherit the same blur. We propose Physics-Guided Flow-Map Matching (PG-FMM), a conditional flow-map model that decouples predictable advection from uncertain small-scale detail. A frozen Lagrangian advection prior transports the radar field and supplies an explicit motion forecast, and a flow-map generative head, conditioned on the past frames and the prior rollout rather than summed onto it, produces sharp stochastic detail in four sampling steps. The prior serves only as guidance, so the head replaces blurred structure instead of inheriting it. Extensive experiments on four radar benchmarks show that PG-FMM outperforms state-of-the-art methods on 18 of 24 metrics, with the largest gains at heavy-rain thresholds, where the critical success index improves by up to 58.9%. The project page can be found at https://neurogica.github.io/PG-FMM.
CommentsAccepted by ACCV 2026
