arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2103.10081cs.CV
收藏

视频超分辨率的自监督自适应算法

Self-Supervised Adaptation for Video Super-Resolution

Hanyang University(汉阳大学)

Jinsu Yoo, Tae Hyun Kim

摘要:

最近的单图像超分辨率(SISR)网络,它可以调整其网络参数,以特定的输入图像,已经显示出有前途的结果,通过利用输入数据以及大型外部数据集内可用的信息。然而,这些自我监督的SISR方法的视频处理的扩展还有待研究。因此,我们提出了一种新的学习算法,允许传统的视频超分辨率(VSR)网络,以适应他们的参数来测试视频帧,而不使用地面实况数据集。通过利用空间和时间上的许多自相似补丁,我们提高了完全预训练的VSR网络的性能,并产生时间上一致的视频帧。此外,我们提出了一个测试时的知识蒸馏技术,加快了适应速度与较少的硬件资源。在我们的实验中,我们证明了我们的新学习算法可以微调最先进的VSR网络,并大大提高了许多基准数据集的性能。

英文摘要:

Recent single-image super-resolution (SISR) networks, which can adapt their network parameters to specific input images, have shown promising results by exploiting the information available within the input data as well as large external datasets. However, the extension of these self-supervised SISR approaches to video handling has yet to be studied. Thus, we present a new learning algorithm that allows conventional video super-resolution (VSR) networks to adapt their parameters to test video frames without using the ground-truth datasets. By utilizing many self-similar patches across space and time, we improve the performance of fully pre-trained VSR networks and produce temporally consistent video frames. Moreover, we present a test-time knowledge distillation technique that accelerates the adaptation speed with less hardware resources. In our experiments, we demonstrate that our novel learning algorithm can fine-tune state-of-the-art VSR networks and substantially elevate performance on numerous benchmark datasets.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑