arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1509.07009cs.CV
收藏

图像超分辨率对其他视觉任务有帮助吗?

Is Image Super-resolution Helpful for Other Vision Tasks?

ETH Zurich(苏黎世联邦理工学院)

Dengxin Dai, Yujian Wang, Yuhua Chen, Luc Van Gool

摘要:

尽管图像超分辨率(ISR)领域取得了很大的进步,在过去的几年中,性能仅仅是感知评估。因此,目前还不清楚ISR是否有助于其他视觉任务。在本文中,我们提出了第一个全面的研究和分析的有用性ISR的其他视觉应用。特别是,六个ISR方法进行了评估四个流行的视觉任务,即边缘检测,语义图像分割,数字识别和场景识别。我们表明,ISR的其他视觉系统的输入图像时,输入图像的低分辨率,提高其性能。我们还研究了四个标准的感知评价标准(即PSNR,SSIM,IFC和NQM)和ISR的视觉任务的有用性之间的相关性。实验表明,它们之间的相关性很好,但感知标准仍然不够准确,不能作为有用性的完全代理。我们希望这项工作将激励社区在实际视觉应用中评估ISR方法,并在输入图像分辨率较低时采用ISR作为其他视觉任务的预处理步骤。

英文摘要:

Despite the great advances made in the field of image super-resolution (ISR) during the last years, the performance has merely been evaluated perceptually. Thus, it is still unclear whether ISR is helpful for other vision tasks. In this paper, we present the first comprehensive study and analysis of the usefulness of ISR for other vision applications. In particular, six ISR methods are evaluated on four popular vision tasks, namely edge detection, semantic image segmentation, digit recognition, and scene recognition. We show that applying ISR to input images of other vision systems does improve their performance when the input images are of low-resolution. We also study the correlation between four standard perceptual evaluation criteria (namely PSNR, SSIM, IFC, and NQM) and the usefulness of ISR to the vision tasks. Experiments show that they correlate well with each other in general, but perceptual criteria are still not accurate enough to be used as full proxies for the usefulness. We hope this work will inspire the community to evaluate ISR methods also in real vision applications, and to adopt ISR as a pre-processing step of other vision tasks if the resolution of their input images is low.

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。

↑