TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK
Image Super-Resolution	BSD100 - 4x upscaling	EDSR	PSNR	27.71	# 11
Image Super-Resolution	BSD100 - 4x upscaling	EDSR	SSIM	0.7420	# 13
Image Super-Resolution	FFHQ 1024 x 1024 - 4x upscaling	EDSR	FID	15.54	# 2
Image Super-Resolution	FFHQ 1024 x 1024 - 4x upscaling	EDSR	MS-SSIM	0.933	# 4
Image Super-Resolution	FFHQ 1024 x 1024 - 4x upscaling	EDSR	PSNR	28.34	# 3
Image Super-Resolution	FFHQ 1024 x 1024 - 4x upscaling	EDSR	SSIM	0.827	# 3
Image Super-Resolution	FFHQ 256 x 256 - 4x upscaling	EDSR	FID	129.14	# 3
Image Super-Resolution	FFHQ 256 x 256 - 4x upscaling	EDSR	MS-SSIM	0.901	# 3
Image Super-Resolution	FFHQ 256 x 256 - 4x upscaling	EDSR	PSNR	22.47	# 4
Image Super-Resolution	FFHQ 256 x 256 - 4x upscaling	EDSR	SSIM	0.706	# 3
Image Super-Resolution	Manga109 - 4x upscaling	EDSR	PSNR	31.02	# 10
Image Super-Resolution	Manga109 - 4x upscaling	EDSR	SSIM	0.9148	# 10
Image Super-Resolution	Set14 - 4x upscaling	EDSR	PSNR	28.80	# 13
Image Super-Resolution	Set14 - 4x upscaling	EDSR	SSIM	0.7876	# 14
Image Super-Resolution	Set5 - 4x upscaling	EDSR	PSNR	32.46	# 11
Image Super-Resolution	Set5 - 4x upscaling	EDSR	SSIM	0.8968	# 14
Image Super-Resolution	Urban100 - 4x upscaling	EDSR	PSNR	26.64	# 12
Image Super-Resolution	Urban100 - 4x upscaling	EDSR	SSIM	0.8033	# 9

🦡 Badges

Include the markdown at the top of your GitHub README.md file to showcase the performance of the model.

Badges are live and will be dynamically updated with the latest ranking of this paper.

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/enhanced-deep-residual-networks-for-single/image-super-resolution-on-ffhq-1024-x-1024-4x)](https://paperswithcode.com/sota/image-super-resolution-on-ffhq-1024-x-1024-4x?p=enhanced-deep-residual-networks-for-single)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/enhanced-deep-residual-networks-for-single/image-super-resolution-on-ffhq-256-x-256-4x)](https://paperswithcode.com/sota/image-super-resolution-on-ffhq-256-x-256-4x?p=enhanced-deep-residual-networks-for-single)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/enhanced-deep-residual-networks-for-single/image-super-resolution-on-manga109-4x)](https://paperswithcode.com/sota/image-super-resolution-on-manga109-4x?p=enhanced-deep-residual-networks-for-single)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/enhanced-deep-residual-networks-for-single/image-super-resolution-on-bsd100-4x-upscaling)](https://paperswithcode.com/sota/image-super-resolution-on-bsd100-4x-upscaling?p=enhanced-deep-residual-networks-for-single)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/enhanced-deep-residual-networks-for-single/image-super-resolution-on-set5-4x-upscaling)](https://paperswithcode.com/sota/image-super-resolution-on-set5-4x-upscaling?p=enhanced-deep-residual-networks-for-single)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/enhanced-deep-residual-networks-for-single/image-super-resolution-on-urban100-4x)](https://paperswithcode.com/sota/image-super-resolution-on-urban100-4x?p=enhanced-deep-residual-networks-for-single)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/enhanced-deep-residual-networks-for-single/image-super-resolution-on-set14-4x-upscaling)](https://paperswithcode.com/sota/image-super-resolution-on-set14-4x-upscaling?p=enhanced-deep-residual-networks-for-single)`

Enhanced Deep Residual Networks for Single Image Super-Resolution

10 Jul 2017 • Bee Lim • Sanghyun Son • Heewon Kim • Seungjun Nah • Kyoung Mu Lee

Recent research on super-resolution has progressed with the development of deep convolutional neural networks (DCNN). In particular, residual learning techniques exhibit improved performance... (read more)

PDF Abstract

Code

Add Remove

thstkdgus35/EDSR-PyTorch

1,236

krasserm/super-resolution

672

LimBee/NTIRE2017

509

Saafke/EDSR_Tensorflow

jamesgolden1/mri_super_resolution

See all 18 implementations

Tasks

Add Remove

IMAGE SUPER-RESOLUTION

SUPER-RESOLUTION

Results from the Paper

Edit

#2 best model for Image Super-Resolution on FFHQ 1024 x 1024 - 4x upscaling

Get a GitHub badge

TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK	LEADERBOARD
Image Super-Resolution	BSD100 - 4x upscaling	EDSR	PSNR	27.71	# 11	Compare
Image Super-Resolution	BSD100 - 4x upscaling	EDSR	SSIM	0.7420	# 13	Compare
Image Super-Resolution	Manga109 - 4x upscaling	EDSR	PSNR	31.02	# 10	Compare
Image Super-Resolution	Manga109 - 4x upscaling	EDSR	SSIM	0.9148	# 10	Compare
Image Super-Resolution	Set14 - 4x upscaling	EDSR	PSNR	28.80	# 13	Compare
Image Super-Resolution	Set14 - 4x upscaling	EDSR	SSIM	0.7876	# 14	Compare
Image Super-Resolution	Set5 - 4x upscaling	EDSR	PSNR	32.46	# 11	Compare
Image Super-Resolution	Set5 - 4x upscaling	EDSR	SSIM	0.8968	# 14	Compare
Image Super-Resolution	Urban100 - 4x upscaling	EDSR	PSNR	26.64	# 12	Compare
Image Super-Resolution	Urban100 - 4x upscaling	EDSR	SSIM	0.8033	# 9	Compare

Results from Other Papers

TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK	COMPARE
Image Super-Resolution	FFHQ 1024 x 1024 - 4x upscaling	EDSR	FID	15.54	# 2	See all
			MS-SSIM	0.933	# 4	See all
			PSNR	28.34	# 3	See all
			SSIM	0.827	# 3	See all
Image Super-Resolution	FFHQ 256 x 256 - 4x upscaling	EDSR	FID	129.14	# 3	See all
			MS-SSIM	0.901	# 3	See all
			PSNR	22.47	# 4	See all
			SSIM	0.706	# 3	See all

Enhanced Deep Residual Networks for Single Image Super-Resolution

Code Edit Add Remove

Tasks Edit Add Remove

Results from the Paper Edit

Results from Other Papers

Code

Add Remove

Tasks

Add Remove

Results from the Paper

Edit