Single-Image Super-Resolution Reconstruction Based on the Differences of Neighboring Pixels
Single-Image Super-Resolution Reconstruction Based on the Differences of Neighboring Pixels
复制标题
DOI：
10.1007/978-3-030-92307-5_61
复制
发表时间：
2022-12
期刊：
影响因子：
--
通讯作者：
Hu Zheng;L. Hakim;Takio Kurita;J. Miyao
中科院分区：
文献类型：
--
作者：
Hu Zheng;L. Hakim;Takio Kurita;J. Miyao
为了提高单幅图像超分辨率(SISR)的性能，采用深度学习技术。然而，大多数现有的基于CNN的SISR方法主要集中在建立更深或更大的网络来提取更重要的高层特征。通常使用目标高分辨率图像和估计图像之间的像素级损失，但很少使用图像中像素之间的邻域关系。另一方面，根据观察，像素的邻域关系包含了丰富的空间结构信息、局部上下文信息和结构知识。基于这一事实，本文从不同的角度利用像素的邻域关系，通过将估计图像和地面真实图像构造一个图，提出利用邻域像素的差异性来正则化CNN。在基准数据集的定量和定性评估方面，所提出的方法优于最先进的方法。
The deep learning technique was used to increase the performance of single image super-resolution (SISR). However, most existing CNN-based SISR approaches primarily focus on establishing deeper or larger networks to extract more significant high-level features. Usually, the pixel-level loss between the target high-resolution image and the estimated image is used, but the neighbor relations between pixels in the image are seldom used. On the other hand, according to observations, a pixel’s neighbor relationship contains rich information about the spatial structure, local context, and structural knowledge. Based on this fact, in this paper, we utilize pixel’s neighbor relationships in a different perspective, and we propose the differences of neighboring pixels to regularize the CNN by constructing a graph from the estimated image and the ground-truth image. The proposed method outperforms the state-of-the-art methods in terms of quantitative and qualitative evaluation of the benchmark datasets.