当前位置: X-MOL 学术IEEE Signal Process. Lett. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
DDet: Dual-path Dynamic Enhancement Network for Real-World Image Super-Resolution
IEEE Signal Processing Letters ( IF 3.9 ) Pub Date : 2020-01-01 , DOI: 10.1109/lsp.2020.2978410
Yukai Shi , Haoyu Zhong , Zhijing Yang , Xiaojun Yang , Liang Lin

Different from traditional image super-resolution task, real image super-resolution(Real-SR) focus on the relationship between real-world high-resolution(HR) and low-resolution(LR) image. Most of the traditional image SR obtains the LR sample by applying a fixed down-sampling operator. Real-SR obtains the LR and HR image pair by incorporating different quality optical sensors. Generally, Real-SR has more challenges as well as broader application scenarios. Previous image SR methods fail to exhibit similar performance on Real-SR as the image data is not aligned inherently. In this article, we propose a Dual-path Dynamic Enhancement Network(DDet) for Real-SR, which addresses the cross-camera image mapping by realizing a dual-way dynamic sub-pixel weighted aggregation and refinement. Unlike conventional methods which stack up massive convolutional blocks for feature representation, we introduce a content-aware framework to study non-inherently aligned image pair in image SR issue. First, we use a content-adaptive component to exhibit the Multi-scale Dynamic Attention(MDA). Second, we incorporate a long-term skip connection with a Coupled Detail Manipulation(CDM) to perform collaborative compensation and manipulation. The above dual-path model is joint into a unified model and works collaboratively. Extensive experiments on the challenging benchmarks demonstrate the superiority of our model.

中文翻译:

DDet:用于真实世界图像超分辨率的双路径动态增强网络

与传统的图像超分辨率任务不同,真实图像超分辨率(Real-SR)侧重于现实世界高分辨率(HR)和低分辨率(LR)图像之间的关系。大多数传统图像SR通过应用固定的下采样算子来获得LR样本。Real-SR 通过结合不同质量的光学传感器获得 LR 和 HR 图像对。一般来说,Real-SR 面临的挑战更多,应用场景也更广。以前的图像 SR 方法无法在 Real-SR 上表现出类似的性能,因为图像数据本身没有对齐。在本文中,我们为 Real-SR 提出了一种双路径动态增强网络(DDet),它通过实现双向动态子像素加权聚合和细化来解决跨相机图像映射问题。与堆叠大量卷积块以进行特征表示的传统方法不同,我们引入了一个内容感知框架来研究图像 SR 问题中的非固有对齐图像对。首先,我们使用内容自适应组件来展示多尺度动态注意力(MDA)。其次,我们将长期跳跃连接与耦合细节操作(CDM)结合起来,以执行协同补偿和操作。上述双路径模型联合成一个统一模型,协同工作。在具有挑战性的基准上进行的大量实验证明了我们模型的优越性。我们将长期跳跃连接与耦合细节操作 (CDM) 结合起来,以执行协同补偿和操作。上述双路径模型联合成一个统一模型,协同工作。在具有挑战性的基准上进行的大量实验证明了我们模型的优越性。我们将长期跳跃连接与耦合细节操作 (CDM) 结合起来,以执行协同补偿和操作。上述双路径模型联合成一个统一模型,协同工作。在具有挑战性的基准上进行的大量实验证明了我们模型的优越性。
更新日期:2020-01-01
down
wechat
bug