Continuous Spatio-Temporal Video Super-Resolution (C-STVSR) aims to simultaneously enhance the spatial resolution and frame rate of videos by arbitrary scale factors, offering greater flexibility than fixed-scale methods that are constrained by predefined upsampling ratios. In recent years, methods based on Implicit Neural Representations (INR) have made significant progress in C-STVSR by learning continuous mappings from spatio-temporal coordinates to pixel values. However, these methods fundamentally rely on dense pixel-wise grid queries, causing computational cost to scale linearly with the number of interpolated frames and severely limiting inference efficiency. We propose GS-STVSR, an ultra-efficient C-STVSR framework based on 2D Gaussian Splatting (2D-GS) that drives the spatiotemporal evolution of Gaussian kernels through continuous motion modeling, bypassing dense grid queries entirely. We exploit the strong temporal stability of covariance parameters for lightweight intermediate fitting, design an optical flow-guided motion module to derive Gaussian position and color at arbitrary time steps, introduce a Covariance resampling alignment module to prevent covariance drift, and propose an adaptive offset window for large-scale motion. Extensive experiments on Vid4, GoPro, and Adobe240 show that GS-STVSR achieves state-of-the-art quality across all benchmarks. Moreover, its inference time remains nearly constant at conventional temporal scales (X2--X8) and delivers over X3 speedup at extreme scales X32, demonstrating strong practical applicability.

翻译：连续时空视频超分辨率重建（C-STVSR）旨在通过任意尺度因子同时提升视频的空间分辨率和帧率，相较于受限于预定义上采样比率的固定尺度方法具有更强的灵活性。近年来，基于隐式神经表征（INR）的方法通过学习从时空坐标到像素值的连续映射，在C-STVSR领域取得了显著进展。然而，这类方法本质上依赖密集的逐像素网格查询，导致计算成本随插值帧数线性增长，严重制约推理效率。我们提出GS-STVSR框架——一种基于二维高斯散点（2D-GS）的超高效C-STVSR方案，通过连续运动建模驱动高斯核的时空演化，从根本上绕开密集网格查询。具体而言，利用协方差参数强时间稳定性实现轻量级中间拟合，设计光流引导的运动模块推导任意时刻高斯位置与颜色，引入协方差重采样对齐模块防止协方差漂移，并针对大尺度运动提出自适应偏移窗口。在Vid4、GoPro和Adobe240数据集上的大量实验表明，GS-STVSR在所有基准测试中均达到最优质量。此外，其推理时间在常规时间尺度（X2-X8）下几乎保持恒定，在极端尺度X32下可实现超过X3倍的加速，展现出强大的实际应用价值。