TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK
Image Super-Resolution	BSD100 - 2x upscaling	HAN+	PSNR	32.45	# 3
Image Super-Resolution	BSD100 - 2x upscaling	HAN+	SSIM	0.8431	# 5
Image Super-Resolution	BSD100 - 3x upscaling	HAN+	PSNR	29.41	# 1
Image Super-Resolution	BSD100 - 3x upscaling	HAN+	SSIM	0.8116	# 2
Image Super-Resolution	BSD100 - 4x upscaling	HAN+	PSNR	27.85	# 5
Image Super-Resolution	BSD100 - 4x upscaling	HAN+	SSIM	0.7454	# 8
Image Super-Resolution	BSD100 - 8x upscaling	HAN+	PSNR	25.04	# 2
Image Super-Resolution	BSD100 - 8x upscaling	HAN+	SSIM	0.6075	# 1
Image Super-Resolution	Manga109 - 2x upscaling	HAN+	PSNR	39.62	# 2
Image Super-Resolution	Manga109 - 2x upscaling	HAN+	SSIM	0.9787	# 3
Image Super-Resolution	Manga109 - 3x upscaling	HAN+	PSNR	34.87	# 2
Image Super-Resolution	Manga109 - 3x upscaling	HAN+	SSIM	0.9509	# 2
Image Super-Resolution	Manga109 - 4x upscaling	HAN+	PSNR	31.73	# 5
Image Super-Resolution	Manga109 - 4x upscaling	HAN+	SSIM	0.9207	# 7
Image Super-Resolution	Manga109 - 8x upscaling	HAN+	PSNR	25.54	# 3
Image Super-Resolution	Manga109 - 8x upscaling	HAN+	SSIM	0.8080	# 3
Image Super-Resolution	Set14 - 2x upscaling	HAN+	PSNR	34.24	# 5
Image Super-Resolution	Set14 - 2x upscaling	HAN+	SSIM	0.9224	# 4
Image Super-Resolution	Set14 - 3x upscaling	HAN+	PSNR	30.79	# 4
Image Super-Resolution	Set14 - 3x upscaling	HAN+	SSIM	0.8487	# 2
Image Super-Resolution	Set14 - 4x upscaling	HAN+	PSNR	28.99	# 6
Image Super-Resolution	Set14 - 4x upscaling	HAN+	SSIM	0.7907	# 12
Image Super-Resolution	Set14 - 8x upscaling	HAN+	PSNR	25.39	# 3
Image Super-Resolution	Set14 - 8x upscaling	HAN+	SSIM	0.6552	# 2
Image Super-Resolution	Set5 - 2x upscaling	HAN+	PSNR	38.33	# 3
Image Super-Resolution	Set5 - 2x upscaling	HAN+	SSIM	0.9299	# 11
Image Super-Resolution	Set5 - 3x upscaling	HAN+	PSNR	34.85	# 3
Image Super-Resolution	Set5 - 3x upscaling	HAN+	SSIM	0.9300	# 2
Image Super-Resolution	Set5 - 4x upscaling	HAN+	PSNR	32.75	# 3
Image Super-Resolution	Set5 - 4x upscaling	HAN+	SSIM	0.9016	# 7
Image Super-Resolution	Set5 - 8x upscaling	HAN+	PSNR	27.47	# 3
Image Super-Resolution	Set5 - 8x upscaling	HAN+	SSIM	0.7920	# 3
Image Super-Resolution	Urban100 - 2x upscaling	HAN+	PSNR	33.53	# 3
Image Super-Resolution	Urban100 - 2x upscaling	HAN+	SSIM	0.9398	# 3
Image Super-Resolution	Urban100 - 3x upscaling	HAN+	PSNR	29.21	# 4
Image Super-Resolution	Urban100 - 3x upscaling	HAN+	SSIM	0.8710	# 2
Image Super-Resolution	Urban100 - 4x upscaling	HAN+	PSNR	27.02	# 11
Image Super-Resolution	Urban100 - 4x upscaling	HAN+	SSIM	0.8131	# 11
Image Super-Resolution	Urban100 - 8x upscaling	HAN+	PSNR	23.20	# 2
Image Super-Resolution	Urban100 - 8x upscaling	HAN+	SSIM	0.6518	# 3

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/single-image-super-resolution-via-a-holistic/image-super-resolution-on-bsd100-3x-upscaling)](https://paperswithcode.com/sota/image-super-resolution-on-bsd100-3x-upscaling?p=single-image-super-resolution-via-a-holistic)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/single-image-super-resolution-via-a-holistic/image-super-resolution-on-bsd100-8x-upscaling)](https://paperswithcode.com/sota/image-super-resolution-on-bsd100-8x-upscaling?p=single-image-super-resolution-via-a-holistic)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/single-image-super-resolution-via-a-holistic/image-super-resolution-on-manga109-2x)](https://paperswithcode.com/sota/image-super-resolution-on-manga109-2x?p=single-image-super-resolution-via-a-holistic)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/single-image-super-resolution-via-a-holistic/image-super-resolution-on-manga109-3x)](https://paperswithcode.com/sota/image-super-resolution-on-manga109-3x?p=single-image-super-resolution-via-a-holistic)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/single-image-super-resolution-via-a-holistic/image-super-resolution-on-urban100-8x)](https://paperswithcode.com/sota/image-super-resolution-on-urban100-8x?p=single-image-super-resolution-via-a-holistic)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/single-image-super-resolution-via-a-holistic/image-super-resolution-on-bsd100-2x-upscaling)](https://paperswithcode.com/sota/image-super-resolution-on-bsd100-2x-upscaling?p=single-image-super-resolution-via-a-holistic)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/single-image-super-resolution-via-a-holistic/image-super-resolution-on-manga109-8x)](https://paperswithcode.com/sota/image-super-resolution-on-manga109-8x?p=single-image-super-resolution-via-a-holistic)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/single-image-super-resolution-via-a-holistic/image-super-resolution-on-set14-8x-upscaling)](https://paperswithcode.com/sota/image-super-resolution-on-set14-8x-upscaling?p=single-image-super-resolution-via-a-holistic)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/single-image-super-resolution-via-a-holistic/image-super-resolution-on-set5-2x-upscaling)](https://paperswithcode.com/sota/image-super-resolution-on-set5-2x-upscaling?p=single-image-super-resolution-via-a-holistic)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/single-image-super-resolution-via-a-holistic/image-super-resolution-on-set5-3x-upscaling)](https://paperswithcode.com/sota/image-super-resolution-on-set5-3x-upscaling?p=single-image-super-resolution-via-a-holistic)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/single-image-super-resolution-via-a-holistic/image-super-resolution-on-set5-4x-upscaling)](https://paperswithcode.com/sota/image-super-resolution-on-set5-4x-upscaling?p=single-image-super-resolution-via-a-holistic)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/single-image-super-resolution-via-a-holistic/image-super-resolution-on-set5-8x-upscaling)](https://paperswithcode.com/sota/image-super-resolution-on-set5-8x-upscaling?p=single-image-super-resolution-via-a-holistic)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/single-image-super-resolution-via-a-holistic/image-super-resolution-on-urban100-2x)](https://paperswithcode.com/sota/image-super-resolution-on-urban100-2x?p=single-image-super-resolution-via-a-holistic)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/single-image-super-resolution-via-a-holistic/image-super-resolution-on-set14-3x-upscaling)](https://paperswithcode.com/sota/image-super-resolution-on-set14-3x-upscaling?p=single-image-super-resolution-via-a-holistic)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/single-image-super-resolution-via-a-holistic/image-super-resolution-on-urban100-3x)](https://paperswithcode.com/sota/image-super-resolution-on-urban100-3x?p=single-image-super-resolution-via-a-holistic)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/single-image-super-resolution-via-a-holistic/image-super-resolution-on-bsd100-4x-upscaling)](https://paperswithcode.com/sota/image-super-resolution-on-bsd100-4x-upscaling?p=single-image-super-resolution-via-a-holistic)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/single-image-super-resolution-via-a-holistic/image-super-resolution-on-set14-2x-upscaling)](https://paperswithcode.com/sota/image-super-resolution-on-set14-2x-upscaling?p=single-image-super-resolution-via-a-holistic)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/single-image-super-resolution-via-a-holistic/image-super-resolution-on-set14-4x-upscaling)](https://paperswithcode.com/sota/image-super-resolution-on-set14-4x-upscaling?p=single-image-super-resolution-via-a-holistic)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/single-image-super-resolution-via-a-holistic/image-super-resolution-on-manga109-4x)](https://paperswithcode.com/sota/image-super-resolution-on-manga109-4x?p=single-image-super-resolution-via-a-holistic)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/single-image-super-resolution-via-a-holistic/image-super-resolution-on-urban100-4x)](https://paperswithcode.com/sota/image-super-resolution-on-urban100-4x?p=single-image-super-resolution-via-a-holistic)`

Single Image Super-Resolution via a Holistic Attention Network

ECCV 2020 · Ben Niu, Weilei Wen, Wenqi Ren, Xiangde Zhang, Lianping Yang, Shuzhen Wang, Kaihao Zhang, Xiaochun Cao, Haifeng Shen ·

Informative features play a crucial role in the single image super-resolution task. Channel attention has been demonstrated to be effective for preserving information-rich features in each layer. However, channel attention treats each convolution layer as a separate process that misses the correlation among different layers. To address this problem, we propose a new holistic attention network (HAN), which consists of a layer attention module (LAM) and a channel-spatial attention module (CSAM), to model the holistic interdependencies among layers, channels, and positions. Specifically, the proposed LAM adaptively emphasizes hierarchical features by considering correlations among layers. Meanwhile, CSAM learns the confidence at all the positions of each channel to selectively capture more informative features. Extensive experiments demonstrate that the proposed HAN performs favorably against the state-of-the-art single image super-resolution approaches.

PDF Abstract ECCV 2020 PDF ECCV 2020 Abstract

Code

Add Remove Mark official

wwlCape/HAN

128

04RR/SOTA-Vision

Tasks

Add Remove

Image Super-Resolution

Single Image Super Resolution

Super-Resolution

Datasets

BSD

Urban100

Set14

Set5

Manga109 BSD100

Results from the Paper

Edit

Ranked #1 on Image Super-Resolution on BSD100 - 3x upscaling

Get a GitHub badge

Task	Dataset	Model	Metric Name	Metric Value	Global Rank	Benchmark
Image Super-Resolution	BSD100 - 2x upscaling	HAN+	PSNR	32.45	# 3	Compare
Image Super-Resolution	BSD100 - 2x upscaling	HAN+	SSIM	0.8431	# 5	Compare
Image Super-Resolution	BSD100 - 3x upscaling	HAN+	PSNR	29.41	# 1	Compare
Image Super-Resolution	BSD100 - 3x upscaling	HAN+	SSIM	0.8116	# 2	Compare
Image Super-Resolution	BSD100 - 4x upscaling	HAN+	PSNR	27.85	# 5	Compare
Image Super-Resolution	BSD100 - 4x upscaling	HAN+	SSIM	0.7454	# 8	Compare
Image Super-Resolution	BSD100 - 8x upscaling	HAN+	PSNR	25.04	# 2	Compare
Image Super-Resolution	BSD100 - 8x upscaling	HAN+	SSIM	0.6075	# 1	Compare
Image Super-Resolution	Manga109 - 2x upscaling	HAN+	PSNR	39.62	# 2	Compare
Image Super-Resolution	Manga109 - 2x upscaling	HAN+	SSIM	0.9787	# 3	Compare
Image Super-Resolution	Manga109 - 3x upscaling	HAN+	PSNR	34.87	# 2	Compare
Image Super-Resolution	Manga109 - 3x upscaling	HAN+	SSIM	0.9509	# 2	Compare
Image Super-Resolution	Manga109 - 4x upscaling	HAN+	PSNR	31.73	# 5	Compare
Image Super-Resolution	Manga109 - 4x upscaling	HAN+	SSIM	0.9207	# 7	Compare
Image Super-Resolution	Manga109 - 8x upscaling	HAN+	PSNR	25.54	# 3	Compare
Image Super-Resolution	Manga109 - 8x upscaling	HAN+	SSIM	0.8080	# 3	Compare
Image Super-Resolution	Set14 - 2x upscaling	HAN+	PSNR	34.24	# 5	Compare
Image Super-Resolution	Set14 - 2x upscaling	HAN+	SSIM	0.9224	# 4	Compare
Image Super-Resolution	Set14 - 3x upscaling	HAN+	PSNR	30.79	# 4	Compare
Image Super-Resolution	Set14 - 3x upscaling	HAN+	SSIM	0.8487	# 2	Compare
Image Super-Resolution	Set14 - 4x upscaling	HAN+	PSNR	28.99	# 6	Compare
Image Super-Resolution	Set14 - 4x upscaling	HAN+	SSIM	0.7907	# 12	Compare
Image Super-Resolution	Set14 - 8x upscaling	HAN+	PSNR	25.39	# 3	Compare
Image Super-Resolution	Set14 - 8x upscaling	HAN+	SSIM	0.6552	# 2	Compare
Image Super-Resolution	Set5 - 2x upscaling	HAN+	PSNR	38.33	# 3	Compare
Image Super-Resolution	Set5 - 2x upscaling	HAN+	SSIM	0.9299	# 11	Compare
Image Super-Resolution	Set5 - 3x upscaling	HAN+	PSNR	34.85	# 3	Compare
Image Super-Resolution	Set5 - 3x upscaling	HAN+	SSIM	0.9300	# 2	Compare
Image Super-Resolution	Set5 - 4x upscaling	HAN+	PSNR	32.75	# 3	Compare
Image Super-Resolution	Set5 - 4x upscaling	HAN+	SSIM	0.9016	# 7	Compare
Image Super-Resolution	Set5 - 8x upscaling	HAN+	PSNR	27.47	# 3	Compare
Image Super-Resolution	Set5 - 8x upscaling	HAN+	SSIM	0.7920	# 3	Compare
Image Super-Resolution	Urban100 - 2x upscaling	HAN+	PSNR	33.53	# 3	Compare
Image Super-Resolution	Urban100 - 2x upscaling	HAN+	SSIM	0.9398	# 3	Compare
Image Super-Resolution	Urban100 - 3x upscaling	HAN+	PSNR	29.21	# 4	Compare
Image Super-Resolution	Urban100 - 3x upscaling	HAN+	SSIM	0.8710	# 2	Compare
Image Super-Resolution	Urban100 - 4x upscaling	HAN+	PSNR	27.02	# 11	Compare
Image Super-Resolution	Urban100 - 4x upscaling	HAN+	SSIM	0.8131	# 11	Compare
Image Super-Resolution	Urban100 - 8x upscaling	HAN+	PSNR	23.20	# 2	Compare
Image Super-Resolution	Urban100 - 8x upscaling	HAN+	SSIM	0.6518	# 3	Compare

Methods

Add Remove

Convolution

Edit Social Preview

Single Image Super-Resolution via a Holistic Attention Network

Code Edit Add Remove Mark official

Tasks Edit Add Remove

Datasets Edit

Results from the Paper Edit

Methods Edit Add Remove

Code

Add Remove Mark official

Tasks

Add Remove

Datasets

Results from the Paper

Edit

Methods

Add Remove