Guided filter-based multi-scale super-resolution reconstruction

CAAI Transactions on Intelligence Technology

article

Xiaomei Feng¹  Jinjiang Li¹  Zhen Hua¹ 

[1] School of Electronic and Communications Engineering, Shandong Technology and Business University;Co-innovation Center of Shandong Colleges and Universities: Future Intelligent Computing, Shandong Technology and Business University

关键词: image resolution;    image texture;    learning (artificial intelligence);    image reconstruction;    image filtering;    high-resolution image;    low-resolution image loss;    super-resolution reconstruction effect;    guided filter-based multiscale super-resolution reconstruction;    learning-based super-resolution reconstruction method;    multiscale super-resolution reconstruction network;    end-to-end super-resolution reconstruction task;    multiscale super-resolution reconstruction method;    guided image filtering;    multiscale super-resolution network;    guide image filter;    newly generated image;    super-resolution reconstruction scheme;    B0290F Interpolation and function approximation (numerical analysis);    B6135 Optical;    image and video signal processing;    B6140B Filtering methods in signal processing;    C5260B Computer vision and image processing techniques;    C6170K Knowledge engineering techniques;   

DOI  :  10.1049/trit.2019.0065

学科分类：数学（综合）

来源: Wiley

【 摘 要 】

The learning-based super-resolution reconstruction method inputs a low-resolution image into a network, and learns a non-linear mapping relationship between low-resolution and high-resolution through the network. In this study, the multi-scale super-resolution reconstruction network is used to fuse the effective features of different scale images, and the non-linear mapping between low resolution and high resolution is studied from coarse to fine to realise the end-to-end super-resolution reconstruction task. The loss of some features of the low-resolution image will negatively affect the quality of the reconstructed image. To solve the problem of incomplete image features in low-resolution, this study adopts the multi-scale super-resolution reconstruction method based on guided image filtering. The high-resolution image reconstructed by the multi-scale super-resolution network and the real high-resolution image are merged by the guide image filter to generate a new image, and the newly generated image is used for secondary training of the multi-scale super-resolution reconstruction network. The newly generated image effectively compensates for the details and texture information lost in the low-resolution image, thereby improving the effect of the super-resolution reconstructed image.Compared with the existing super-resolution reconstruction scheme, the accuracy and speed of super-resolution reconstruction are improved.

【 授权许可】

CC BY|CC BY-ND|CC BY-NC|CC BY-NC-ND