TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK
Stereo Image Super-Resolution	Flickr1024 - 2x upscaling	PASSRnet	PSNR	28.38	# 6
Stereo Image Super-Resolution	Flickr1024 - 4x upscaling	PASSRnet	PSNR	23.31	# 6
Stereo Image Super-Resolution	KITTI2012 - 2x upscaling	PASSRnet	PSNR	30.81	# 3
Image Super-Resolution	KITTI 2012 - 2x upscaling	PASSRnet	PSNR	30.65	# 1
Image Super-Resolution	KITTI 2012 - 4x upscaling	PASSRnet	PSNR	26.26	# 1
Stereo Image Super-Resolution	KITTI2012 - 4x upscaling	PASSRnet	PSNR	26.34	# 6
Image Super-Resolution	KITTI 2015 - 2x upscaling	PASSRnet	PSNR	29.78	# 1
Stereo Image Super-Resolution	KITTI2015 - 2x upscaling	PASSRnet	PSNR	30.60	# 6
Image Super-Resolution	KITTI 2015 - 4x upscaling	PASSRnet	PSNR	25.43	# 1
Stereo Image Super-Resolution	KITTI2015 - 4x upscaling	PASSRnet	PSNR	26.08	# 6
Stereo Image Super-Resolution	Middlebury - 2x upscaling	PASSRnet	PSNR	34.23	# 7
Image Super-Resolution	Middlebury - 2x upscaling	PASSRnet	PSNR	34.05	# 1
Stereo Image Super-Resolution	Middlebury - 4x upscaling	PASSRnet	PSNR	28.72	# 6
Image Super-Resolution	Middlebury - 4x upscaling	PASSRnet	PSNR	28.63	# 1

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/learning-parallax-attention-for-stereo-image/image-super-resolution-on-kitti-2012-2x)](https://paperswithcode.com/sota/image-super-resolution-on-kitti-2012-2x?p=learning-parallax-attention-for-stereo-image)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/learning-parallax-attention-for-stereo-image/image-super-resolution-on-kitti-2012-4x)](https://paperswithcode.com/sota/image-super-resolution-on-kitti-2012-4x?p=learning-parallax-attention-for-stereo-image)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/learning-parallax-attention-for-stereo-image/image-super-resolution-on-kitti-2015-2x)](https://paperswithcode.com/sota/image-super-resolution-on-kitti-2015-2x?p=learning-parallax-attention-for-stereo-image)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/learning-parallax-attention-for-stereo-image/image-super-resolution-on-kitti-2015-4x)](https://paperswithcode.com/sota/image-super-resolution-on-kitti-2015-4x?p=learning-parallax-attention-for-stereo-image)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/learning-parallax-attention-for-stereo-image/image-super-resolution-on-middlebury-2x)](https://paperswithcode.com/sota/image-super-resolution-on-middlebury-2x?p=learning-parallax-attention-for-stereo-image)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/learning-parallax-attention-for-stereo-image/image-super-resolution-on-middlebury-4x)](https://paperswithcode.com/sota/image-super-resolution-on-middlebury-4x?p=learning-parallax-attention-for-stereo-image)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/learning-parallax-attention-for-stereo-image/stereo-image-super-resolution-on-kitti2012-2x-1)](https://paperswithcode.com/sota/stereo-image-super-resolution-on-kitti2012-2x-1?p=learning-parallax-attention-for-stereo-image)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/learning-parallax-attention-for-stereo-image/stereo-image-super-resolution-on-flickr1024-1)](https://paperswithcode.com/sota/stereo-image-super-resolution-on-flickr1024-1?p=learning-parallax-attention-for-stereo-image)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/learning-parallax-attention-for-stereo-image/stereo-image-super-resolution-on-flickr1024-2)](https://paperswithcode.com/sota/stereo-image-super-resolution-on-flickr1024-2?p=learning-parallax-attention-for-stereo-image)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/learning-parallax-attention-for-stereo-image/stereo-image-super-resolution-on-kitti2012-4x)](https://paperswithcode.com/sota/stereo-image-super-resolution-on-kitti2012-4x?p=learning-parallax-attention-for-stereo-image)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/learning-parallax-attention-for-stereo-image/stereo-image-super-resolution-on-kitti2015-2x)](https://paperswithcode.com/sota/stereo-image-super-resolution-on-kitti2015-2x?p=learning-parallax-attention-for-stereo-image)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/learning-parallax-attention-for-stereo-image/stereo-image-super-resolution-on-kitti2015-4x)](https://paperswithcode.com/sota/stereo-image-super-resolution-on-kitti2015-4x?p=learning-parallax-attention-for-stereo-image)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/learning-parallax-attention-for-stereo-image/stereo-image-super-resolution-on-middlebury)](https://paperswithcode.com/sota/stereo-image-super-resolution-on-middlebury?p=learning-parallax-attention-for-stereo-image)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/learning-parallax-attention-for-stereo-image/stereo-image-super-resolution-on-middlebury-1)](https://paperswithcode.com/sota/stereo-image-super-resolution-on-middlebury-1?p=learning-parallax-attention-for-stereo-image)`

Learning Parallax Attention for Stereo Image Super-Resolution

CVPR 2019 · Longguang Wang, Yingqian Wang, Zhengfa Liang, Zaiping Lin, Jungang Yang, Wei An, Yulan Guo ·

Stereo image pairs can be used to improve the performance of super-resolution (SR) since additional information is provided from a second viewpoint. However, it is challenging to incorporate this information for SR since disparities between stereo images vary significantly. In this paper, we propose a parallax-attention stereo superresolution network (PASSRnet) to integrate the information from a stereo image pair for SR. Specifically, we introduce a parallax-attention mechanism with a global receptive field along the epipolar line to handle different stereo images with large disparity variations. We also propose a new and the largest dataset for stereo image SR (namely, Flickr1024). Extensive experiments demonstrate that the parallax-attention mechanism can capture correspondence between stereo images to improve SR performance with a small computational and memory cost. Comparative results show that our PASSRnet achieves the state-of-the-art performance on the Middlebury, KITTI 2012 and KITTI 2015 datasets.

PDF Abstract CVPR 2019 PDF CVPR 2019 Abstract

Code

Add Remove Mark official

LongguangWang/PASSRnet official

298

Tasks

Add Remove

Image Super-Resolution

Stereo Image Super-Resolution

Super-Resolution

Datasets

KITTI

Middlebury

Results from the Paper

Edit

Ranked #1 on Image Super-Resolution on KITTI 2012 - 4x upscaling

Get a GitHub badge

Task	Dataset	Model	Metric Name	Metric Value	Global Rank	Benchmark
Stereo Image Super-Resolution	Flickr1024 - 2x upscaling	PASSRnet	PSNR	28.38	# 6	Compare
Stereo Image Super-Resolution	Flickr1024 - 4x upscaling	PASSRnet	PSNR	23.31	# 6	Compare
Stereo Image Super-Resolution	KITTI2012 - 2x upscaling	PASSRnet	PSNR	30.81	# 3	Compare
Image Super-Resolution	KITTI 2012 - 2x upscaling	PASSRnet	PSNR	30.65	# 1	Compare
Image Super-Resolution	KITTI 2012 - 4x upscaling	PASSRnet	PSNR	26.26	# 1	Compare
Stereo Image Super-Resolution	KITTI2012 - 4x upscaling	PASSRnet	PSNR	26.34	# 6	Compare
Image Super-Resolution	KITTI 2015 - 2x upscaling	PASSRnet	PSNR	29.78	# 1	Compare
Stereo Image Super-Resolution	KITTI2015 - 2x upscaling	PASSRnet	PSNR	30.60	# 6	Compare
Image Super-Resolution	KITTI 2015 - 4x upscaling	PASSRnet	PSNR	25.43	# 1	Compare
Stereo Image Super-Resolution	KITTI2015 - 4x upscaling	PASSRnet	PSNR	26.08	# 6	Compare
Stereo Image Super-Resolution	Middlebury - 2x upscaling	PASSRnet	PSNR	34.23	# 7	Compare
Image Super-Resolution	Middlebury - 2x upscaling	PASSRnet	PSNR	34.05	# 1	Compare
Stereo Image Super-Resolution	Middlebury - 4x upscaling	PASSRnet	PSNR	28.72	# 6	Compare
Image Super-Resolution	Middlebury - 4x upscaling	PASSRnet	PSNR	28.63	# 1	Compare

Methods

Add Remove

No methods listed for this paper. Add relevant methods here

Edit Social Preview

Learning Parallax Attention for Stereo Image Super-Resolution

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