Deep-learning video super-resolution has progressed rapidly, but climate applications typically super-resolve (increase resolution) either space or time, and joint spatiotemporal models are often designed for a single pair of super-resolution (SR) factors (upscaling spatial and temporal ratio between the low-resolution sequence and the high-resolution sequence), limiting transfer across spatial resolutions and temporal cadences (frame rates). We present a scale-adaptive framework that reuses the same architecture across factors by decomposing spatiotemporal SR into a deterministic prediction of the conditional mean, with attention, and a residual conditional diffusion model, with an optional mass-conservation (same precipitation amount in inputs and outputs) transform to preserve aggregated totals. Assuming that larger SR factors primarily increase underdetermination (hence required context and residual uncertainty) rather than changing the conditional-mean structure, scale adaptivity is achieved by retuning three factor-dependent hyperparameters before retraining: the diffusion noise schedule amplitude beta (larger for larger factors to increase diversity), the temporal context length L (set to maintain comparable attention horizons across cadences) and optionally a third, the mass-conservation function f (tapered to limit the amplification of extremes for large factors). Demonstrated on reanalysis precipitation over France (Comephore), the same architecture spans super-resolution factors from 1 to 25 in space and 1 to 6 in time, yielding a reusable architecture and tuning recipe for joint spatiotemporal super-resolution across scales.

翻译：深度学习视频超分辨率技术取得了快速发展，但气候应用通常仅对空间或时间维度进行超分辨率（分辨率提升），而联合时空模型往往针对单一超分辨率因子对（低分辨率序列与高分辨率序列之间的空间和时间上采样比值）设计，限制了模型在不同空间分辨率和时间帧率间的迁移能力。我们提出了一种尺度自适应框架，通过将时空超分辨率分解为基于注意力机制的确定性条件均值预测和残差条件扩散模型，并可选配质量守恒变换（确保输入与输出的总降水量一致）以保持聚合总量，从而在不同因子下复用同一架构。假设更大的超分辨率因子主要增加欠定性（因此需要更多上下文信息和残差不确定性）而非改变条件均值结构，尺度自适应性通过重训练前调整三个因子相关超参数实现：扩散噪声调度幅度β（因子越大则幅度越大以增强多样性）、时间上下文长度L（设置为保持不同帧率下注意力范围可比），以及可选的第三个参数——质量守恒函数f（通过渐近设计限制大因子下极端值的放大）。在法国Comephore再分析降水数据上的实验表明，该架构可覆盖空间超分辨率因子1至25和时间因子1至6，为跨尺度的联合时空超分辨率提供了可复用的架构与调参方案。