计算机科学
人工智能
匹配(统计)
图像(数学)
计算机视觉
分辨率(逻辑)
比例(比率)
特征(语言学)
图像分辨率
模式识别(心理学)
特征匹配
数学
语言学
统计
物理
哲学
量子力学
作者
Kai Hu,Ran Chen,Zhong-Qiu Zhao
标识
DOI:10.1007/978-981-99-4742-3_8
摘要
Image super-resolution aims to recover high-resolution (HR) images from corresponding low-resolution (LR) images, but it is prone to lose significant details in reconstruction progress. Reference-based image super-resolution can produce realistic textures using an external reference (Ref) image, thus reconstructing pleasant images. Despite the remarkable advancement, there are two critical challenges in reference-based image super-resolution. One is that it is difficult to match the correspondence between LR and Ref images when they are significantly different. The other is how the details of the Ref image are accurately transferred to the LR image. In order to solve these issues, we propose improved feature extraction and matching method to find the matching relationship corresponding to the LR and Ref images more accurately, propose cross-scale dynamic correction module to use multiple scale related textures to compensate for more information. Extensive experimental results over multiple datasets demonstrate that our method is better than the baseline model on both quantitative and qualitative evaluations.
科研通智能强力驱动
Strongly Powered by AbleSci AI