computer-vision

Stereo Image Super-Resolution

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in stereo-image-super-resolution

Trend

Dataset

Best Model

Actions

Flickr1024 - 2x upscaling

Middlebury - 4x upscaling

Libraries

i

Use these libraries to find stereo-image-super-resolution models and implementations

Datasets

Subtasks

No subtasks available.

Most implemented papers

NAFSSR: Stereo Image Super-Resolution Using NAFNet

Liangyu Chen, Xiaojie Chu, Wenqing Yu•Mon Apr 18 2022

This paper inherits a strong and simple image restoration model, NAFNet, for single-view feature extraction and ex-tends it by adding cross attention modules to fuse features between views to adapt to binocular scenarios.

153

Content

Middlebury - 2x upscaling

Flickr1024 - 4x upscaling

KITTI2012 - 4x upscaling

KITTI2015 - 4x upscaling

KITTI2015 - 2x upscaling

KITTI2012 - 2x upscaling

0

Paper Graph

Learning Parallax Attention for Stereo Image Super-Resolution

Yingqian Wang, Longguang Wang, Jungang Yang, W. An, Yulan Guo, Zhengfa Liang, Zaiping Lin•Wed Mar 13 2019

A parallax-attention mechanism with a global receptive field along the epipolar line to handle different stereo images with large disparity variations is introduced and a new and the largest dataset for stereo image SR is proposed.

273 0

Paper Graph

Symmetric Parallax Attention for Stereo Image Super-Resolution

Xinyi Ying, Yingqian Wang, Longguang Wang, Jungang Yang, W. An, Yulan Guo•Fri Nov 06 2020

This paper proposes a symmetric bi-directional parallax attention module (biPAM) and an inline occlusion handling scheme to effectively interact cross-view information and designs a Siamese network equipped with a biPAM to super-resolve both sides of views in a highly symmetric manner.

100 0

Paper Graph

Feedback Network for Mutually Boosted Stereo Image Super-Resolution and Disparity Estimation

Qi Dai, Juncheng Li, Qiaosi Yi, Faming Fang, Guixu Zhang•Tue Jun 01 2021

A Stereo Super-Resolution and Disparity Estimation Feedback Network (SSRDE-FNet), which simultaneously handles the stereo image super-resolution and disparity estimation in a unified framework and interact them with each other to further improve their performance.

64 0

Paper Graph

Parallax Attention for Unsupervised Stereo Correspondence Learning

Yingqian Wang, Longguang Wang, Jungang Yang, W. An, Zhengfa Liang, Zaiping Lin, Yulan Guo•Tue Sep 15 2020

A generic parallax-attention mechanism (PAM) to capture stereo correspondence regardless of disparity variations is proposed and Experimental results show that the PAM is generic and can effectively learn stereo correspondence under large disparity variations in an unsupervised manner.

138 0

Paper Graph

Cross-View Hierarchy Network for Stereo Image Super-Resolution

Wenbin Zou, Hong-xia Gao, Liang Chen, Yunchen Zhang, Mingchao Jiang, Zhongxin Yu, Ming Tan•Wed Apr 12 2023

A cross-hierarchy information mining block (CHIMB) is designed that leverages channel attention and large kernel convolution attention to extract both global and local features from the intra-view, enabling the efficient restoration of accurate texture details.

15 0

Paper Graph

SwinFIR: Revisiting the SwinIR with Fast Fourier Convolution and Improved Training for Image Super-Resolution

Dafeng Zhang, Feiyu Huang, Shizhuo Liu, Xiaobing Wang, Zhezhu Jin•Tue Aug 23 2022

This work proposes SwinFIR to extend SwinIR by replacing Fast Fourier Convolution (FFC) components, which have the image-wide receptive field, and revisits other advanced techniques, i.e, data augmentation, pre-training, and feature ensemble to improve the effect of image reconstruction.

129 0

Paper Graph

Refusion: Enabling Large-Size Realistic Image Restoration with Latent-Space Diffusion Models

Ziwei Luo, Fredrik K. Gustafsson, Zhengli Zhao, Jens Sjolund, T. Schon•Sun Apr 16 2023

This work enhances the diffusion model in several aspects such as network architecture, noise level, denoising steps, training image size, and optimizer/scheduler, and shows that tuning these hyperparameters allows the model to achieve better performance on both distortion and perceptual scores.

164 0

Paper Graph

Toward Real World Stereo Image Super-Resolution via Hybrid Degradation Model and Discriminator for Implied Stereo Image Information

Qinquan Gao, Yuanbo Zhou, Yuyang Xue, Jiang Bi, Wenlin He, Xinlin Zhang, Jiajun Zhang, Wei Deng, Ruofeng Nie, Junlin Lan, Tong Tong•Tue Dec 12 2023

A novel approach is proposed that integrates a implicit stereo information discriminator and a hybrid degradation model that ensures effective enhancement while preserving disparity consistency, and demonstrates impressive performance on synthetic and real datasets.

3 0

Paper Graph

Adding a benchmark result helps the community track progress.