无时序之时：面向时空超分辨率的伪时序表征
Time Without Time: Pseudo-Temporal Representation for Space-Time Super-Resolution
把单张图像复制成伪时序视频、并在各帧独立零填充随机像素区域，从而用纯图像数据集预训练 STVSR 网络；这种「无需真实视频即可预训练视频复原模型」的构造方式，可直接迁移到去噪、去模糊、帧插值等需要时序聚合的底层视觉任务。
原文依据 Each training sample is constructed by duplicating a single image into a pseudo-temporal video and independently zero-filling random pixel regions across its frames.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论时空视频超分辨率（STVSR）是一项旨在同时在空间与时间维度上对视频进行上采样的任务。以往关于 STVSR 的研究主要集中于任务特定的架构与建模范式，而有效的预训练策略仍鲜有探索。本文提出一种面向 STVSR 网络的伪时序时空重建预训练框架，使图像数据集得以被有效利用——这类数据天然提供了强空间线索。每个训练样本通过将单张图像复制为伪时序视频、并在其各帧上独立地对随机像素区域做零填充而构建。我们并未设计单独的预训练模块，而是在与空间复原和跨帧聚合这一核心目标相一致的任务上预训练 STVSR 网络。模型学习从退化的伪时序输入中重建出干净、时空分辨率更高的输出，并引入调制因子以促使模型更关注困难区域。大量实验表明，我们这一简单的预训练显著提升了 STVSR 性能，并优于现有的视频表征学习方法。我们注意到，即使在预训练与微调数据量有限的情况下，本方法依然有效。
英文原文摘要 1303 字符
Space-time video super-resolution (STVSR) is a task aimed at simultaneously upsampling a video in both spatial and temporal dimensions. Previous studies on STVSR have primarily focused on task-specific architectures and modeling paradigms, while effective pretraining strategies remain underexplored. In this paper, we propose a pseudo-temporal space-time reconstruction pretraining framework for STVSR networks that enables effective use of image datasets, which naturally provide strong spatial cues. Each training sample is constructed by duplicating a single image into a pseudo-temporal video and independently zero-filling random pixel regions across its frames. Instead of designing a separate pretraining module, we pretrain the STVSR network on a task aligned with its core objectives of spatial restoration and cross-frame aggregation. The model learns to reconstruct clean, higher-spatio-temporal-resolution outputs from degraded, pseudo-temporal inputs, with a modulation factor encouraging greater focus on difficult regions. Extensive experiments show that our simple pretraining significantly improves STVSR performance and outperforms existing video representation learning approaches. We note our method is effective even when pretraining and finetuning with a limited quantity of data.