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 2106.04090cs.CVeess.IV
收藏

基于参考的图像超分辨率变分自编码器

Variational AutoEncoder for Reference based Image Super-Resolution

Caritas Institute of Higher Education(明爱专上学院);The Hong Kong Polytechnic University(香港理工大学)

Zhi-Song Liu, Wan-Chi Siu, Li-Wen Wang

摘要:

本文提出了一种基于变分自编码器(RefVAE)的参考图像超分辨率方法。现有的最先进的方法主要集中在单个图像的超分辨率上,其在大的上采样因子上不能很好地执行,例如,8 $\times$。我们提出了一种基于参考的图像超分辨率,其中任意图像可以作为超分辨率的参考。即使使用随机映射或低分辨率图像本身,所提出的RefVAE也可以将知识从参考转移到超分辨率图像。根据不同的参考文献,该方法可以从隐藏的超分辨率空间生成不同版本的超分辨率图像。除了使用不同的数据集进行PSNR和SSIM的一些标准评估外,我们还参加了NTIRE2021 SR Space挑战赛,并提供了我们方法的随机性评估结果。与其他最先进的方法相比,我们的方法实现了更高的多样性分数。

英文摘要:

In this paper, we propose a novel reference based image super-resolution approach via Variational AutoEncoder (RefVAE). Existing state-of-the-art methods mainly focus on single image super-resolution which cannot perform well on large upsampling factors, e.g., 8$\times$. We propose a reference based image super-resolution, for which any arbitrary image can act as a reference for super-resolution. Even using random map or low-resolution image itself, the proposed RefVAE can transfer the knowledge from the reference to the super-resolved images. Depending upon different references, the proposed method can generate different versions of super-resolved images from a hidden super-resolution space. Besides using different datasets for some standard evaluations with PSNR and SSIM, we also took part in the NTIRE2021 SR Space challenge and have provided results of the randomness evaluation of our approach. Compared to other state-of-the-art methods, our approach achieves higher diverse scores.

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。

↑