arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.16673cs.CV
收藏

图像超分辨率的跨尺度内图神经网络

Cross-Scale Internal Graph Neural Network for Image Super-Resolution

Nanyang Technological University(南洋理工大学);SenseTime Research(商汤科技研究院);Harbin Institute of Technology(哈尔滨工业大学)

Shangchen Zhou, Jiawei Zhang, Wangmeng Zuo, Chen Change Loy

摘要:

自然图像的非局部自相似性作为一种有效的先验信息在图像复原中得到了广泛的研究。然而,对于单个图像超分辨率(SISR),大多数现有的深度非局部方法(例如,非局部神经网络)仅利用低分辨率(LR)输入图像的相同尺度内的类似块。因此,恢复仅限于使用相同尺度的信息,而忽略了来自其他尺度的潜在高分辨率(HR)线索。在本文中,我们探讨了跨尺度补丁递归性质的自然图像,即,类似的斑块往往在不同尺度上重复出现多次。这是实现使用一种新的跨尺度内部图神经网络(IGNN)。具体来说,我们动态地构建一个跨尺度图,通过搜索k-最近邻补丁在下采样的LR图像中的LR图像中的每个查询补丁。然后,我们得到相应的k HR相邻块在LR图像和聚合它们自适应根据所构造的图的边缘标签。以这种方式,HR信息可以从k个HR相邻块传递到LR查询块,以帮助其恢复更详细的纹理。此外,这些内部图像特定的LR/HR样本也是对从训练数据集学习的外部信息的重要补充。大量的实验证明了IGNN对最先进的SISR方法,包括现有的非本地网络的标准基准测试的有效性。

英文摘要:

Non-local self-similarity in natural images has been well studied as an effective prior in image restoration. However, for single image super-resolution (SISR), most existing deep non-local methods (e.g., non-local neural networks) only exploit similar patches within the same scale of the low-resolution (LR) input image. Consequently, the restoration is limited to using the same-scale information while neglecting potential high-resolution (HR) cues from other scales. In this paper, we explore the cross-scale patch recurrence property of a natural image, i.e., similar patches tend to recur many times across different scales. This is achieved using a novel cross-scale internal graph neural network (IGNN). Specifically, we dynamically construct a cross-scale graph by searching k-nearest neighboring patches in the downsampled LR image for each query patch in the LR image. We then obtain the corresponding k HR neighboring patches in the LR image and aggregate them adaptively in accordance to the edge label of the constructed graph. In this way, the HR information can be passed from k HR neighboring patches to the LR query patch to help it recover more detailed textures. Besides, these internal image-specific LR/HR exemplars are also significant complements to the external information learned from the training dataset. Extensive experiments demonstrate the effectiveness of IGNN against the state-of-the-art SISR methods including existing non-local networks on standard benchmarks.

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。

↑