Kernel Modeling Super-Resolution on Real Low-Resolution Images

Ruofan Zhou     Sabine Süsstrunk
Image and Visual Representation Lab
École Polytechnique Fédérale de Lausanne

- Supplementary Material -

project page

In Section 4.3 and Section 4.4 in the paper, we report the quantitative results on X4 super-resolution, here we provide the qualitative comparsion of different SR networks. Below we show two examples of X4 super-resolution results on using a Gaussian blur kernel as blur kernel:

SRCNN[3]	VDSR[4]	EDSR[1]	DBPN[2]	KMSR

SRCNN[3]	VDSR[4]	EDSR[1]	DBPN[2]	KMSR

Below we show two examples of X4 super-resolution results on using a realistic blur kernel estimated in DPED-testing as blur kernel:

SRCNN[3]	VDSR[4]	EDSR[1]	DBPN[2]	KMSR

SRCNN[3]	VDSR[4]	EDSR[1]	DBPN[2]	KMSR

Reference:
[1] Lim Bee, Son Sanghyun, Kim Heewon, Nah Seungjun. Lee Kyoung Mu. "Enhanced Deep Residual Networks for Single Image Super-Resolution", in IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2017
[2] Haris Muhammad, Shakhnarovich Greg, Ukita Norimichi. "Deep Back-Projection Networks for Super-Resolution", in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018
[3] Chao Dong, Chen Change Loy, Kaiming He, Xiaoou Tang. "Image Super-Resolution Using Deep Convolutional Networks", in IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2015
[4] Jiwon Kim, Jung Kwon Lee, Kyoung Mu Lee. "Accurate Image Super-Resolution Using Very Deep Convolutional Networks", in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016