잔여 밀집 및 채널 집중 기법을 갖는 재귀적 경량 네트워크 기반의 단일 이미지 초해상도 기법

다국어 초록 (Multilingual Abstract)

With the recent development of deep convolutional neural network learning, deep learning techniques applied to single image super-resolution are showing good results. One of the existing deep learning-based super-resolution techniques is RDN(Residual Dense Network), in which the initial feature information is transmitted to the last layer using residual dense blocks, and subsequent layers are restored using input information of previous layers. However, if all hierarchical features are connected and learned and a large number of residual dense blocks are stacked, despite good performance, a large number of parameters and huge computational load are needed, so it takes a lot of time to learn a network and a slow processing speed, and it is not applicable to a mobile system. In this paper, we use the residual dense structure, which is a continuous memory structure that reuses previous information, and the residual dense channel attention block using the channel attention method that determines the importance according to the feature map of the image. We propose a method that can increase the depth to obtain a large receptive field and maintain a concise model at the same time. As a result of the experiment, the proposed network obtained PSNR as low as 0.205dB on average at 4× magnification compared to RDN, but about 1.8 times faster processing speed, about 10 times less number of parameters and about 1.74 times less computation.

참고문헌 (Reference)

1 K. Simonyan, "Very deep convolutional networks for large-scale image recognition" 2015

2 C. Ren, "Single Image Super-Resolution via Adaptive High-Dimensional Non-Local Total Variation and Adaptive Geometric Feature" 90-106, 2017

3 K. Zhang, "Single Image Super-Resolution With Non-Local Means and Steering Kernel Regression" 4544-4556, 2012

4 J. -B. Huang, "Single Image Super-Resolution From Transformed Self -Exemplars" 5197-5206, 2015

5 Y. Romano, "Single Image Interpolation Via Adaptive Nonlocal Sparsity-Based Modeling" 3085-3098, 2014

6 Zhang, "Residual dense network for image super-resolution" 2472-2481, 2018

7 W. Shi, "Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network" 1874-1883, 2016

8 R. Zeyde, "On single image scale-up using sparse-representations" 711-730, 2012

9 V. Papyan, "Multi-Scale Patch-Based Image Restoration" 249-261, 2016

10 Bevilacqua, "Low-complexity single-image super-resolution based on nonnegative neighbor embedding" 135.1-135.10, 2012

11 H. A. Aly, "Image up-sampling using total-variation regularization with a new observation model" 1647-1659, 2005

12 Y. Tai, "Image super-resolution via deep recursive residual network" 2790-2798, 2017

13 Y. Zhang, "Image super-resolution using very deep residual channel attention networks" 286-301, 2018

14 C. Dong, "Image Super-Resolution Using Deep Convolutional Networks" 295-307, 2016

15 X. Zhang, "Image Interpolation by Adaptive 2-D Autoregressive Modeling and Soft-Decision Estimation" 887-896, 2008

16 G. Huang, "Densely Connected Convolutional Networks" 2261-2269, 2017

17 W. Ye, "Convolutional Edge Diffusion for Fast Contrast-guided Image Interpolation" 1260-1264, 2016

18 J. Kim, "Accurate image super resolution using very deep convolutional networks" 1646-1654, 2016

19 D. Martin, "A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics" 416-423, 2001