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 2201.04364cs.CV
收藏

SCSNet:一种同时学习图像彩色化和超分辨率的有效范例

SCSNet: An Efficient Paradigm for Learning Simultaneously Image Colorization and Super-Resolution

APRIL Lab, Zhejiang University(浙江大学 APRIL 实验室);Youtu Lab, Tencent(腾讯优图实验室)

Jiangning Zhang, Chao Xu, Jian Li, Yue Han, Yabiao Wang, Ying Tai, Yong Liu

摘要:

在低分辨率灰度图像恢复的实际应用中,一般需要对目标设备分别进行图像彩色化、超分辨率和降采样操作。然而,这种流水线对于独立的进程来说是冗余和低效的,并且一些内部特征可以被共享。因此,我们提出了一个有效的范例来执行{S} imultimate图像{C}着色和{S}分辨率(SCS),并提出了一个端到端的SCSNet来实现这一目标。该方法由两部分组成:用于学习颜色信息的着色分支,采用所提出的即插即用\emph{Pyramid Valve Cross Attention}(PVCAttn)模块来聚合源图像和参考图像之间的特征映射;以及用于集成颜色和纹理信息来预测目标图像的超分辨率分支,其使用所设计的\emph{Continuous Pixel Mapping}(CPM)模块来预测连续放大的高分辨率图像。此外,我们的SCSNet支持自动和参考模式,更灵活的实际应用。大量的实验证明了我们的方法在生成真实图像方面优于最先进的方法,例如,与自动和参考模式的当前最佳分数相比,FID分别平均降低1.8 $\downarrow$和5.1 $\downarrow$,同时拥有更少的参数(超过$\times$ 2 $\downarrow$)和更快的运行速度(超过$\times$ 3 $\uparrow$)。

英文摘要:

In the practical application of restoring low-resolution gray-scale images, we generally need to run three separate processes of image colorization, super-resolution, and dows-sampling operation for the target device. However, this pipeline is redundant and inefficient for the independent processes, and some inner features could have been shared. Therefore, we present an efficient paradigm to perform {S}imultaneously Image {C}olorization and {S}uper-resolution (SCS) and propose an end-to-end SCSNet to achieve this goal. The proposed method consists of two parts: colorization branch for learning color information that employs the proposed plug-and-play \emph{Pyramid Valve Cross Attention} (PVCAttn) module to aggregate feature maps between source and reference images; and super-resolution branch for integrating color and texture information to predict target images, which uses the designed \emph{Continuous Pixel Mapping} (CPM) module to predict high-resolution images at continuous magnification. Furthermore, our SCSNet supports both automatic and referential modes that is more flexible for practical application. Abundant experiments demonstrate the superiority of our method for generating authentic images over state-of-the-art methods, e.g., averagely decreasing FID by 1.8$\downarrow$ and 5.1 $\downarrow$ compared with current best scores for automatic and referential modes, respectively, while owning fewer parameters (more than $\times$2$\downarrow$) and faster running speed (more than $\times$3$\uparrow$).

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。

↑