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

@article{Dai2021FeedbackNF,
  title={Feedback Network for Mutually Boosted Stereo Image Super-Resolution and Disparity Estimation},
  author={Qi Dai and Juncheng Li and Qiaosi Yi and Faming Fang and Guixu Zhang},
  journal={Proceedings of the 29th ACM International Conference on Multimedia},
  year={2021}
}
  • Qi Dai, Juncheng Li, Guixu Zhang
  • Published 2 June 2021
  • Computer Science
  • Proceedings of the 29th ACM International Conference on Multimedia
Under stereo settings, the problem of image super-resolution (SR) and disparity estimation are interrelated that the result of each problem could help to solve the other. The effective exploitation of correspondence between different views facilitates the SR performance, while the high-resolution (HR) features with richer details benefit the correspondence estimation. According to this motivation, we propose a Stereo Super-Resolution and Disparity Estimation Feedback Network (SSRDE-FNet), which… 

Figures and Tables from this paper

NAFSSR: Stereo Image Super-Resolution Using NAFNet
TLDR
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.
NTIRE 2022 Challenge on Stereo Image Super-Resolution: Methods and Results
TLDR
The 1st NTIRE challenge on stereo image super-resolution (restoration of rich details in a pair of low-resolution stereo images) is summarized with a focus on new solutions and results.
From Beginner to Master: A Survey for Deep Learning-based Single-Image Super-Resolution
TLDR
This survey gives an overview of DL-based SISR methods and group them according to their targets, such as reconstruction efficiency, reconstruction accuracy, and perceptual accuracy, as well as introducing some related works, including benchmark datasets, upsampling methods, optimization objectives, and image quality assessment methods.

References

SHOWING 1-10 OF 42 REFERENCES
Disparity-Aware Domain Adaptation in Stereo Image Restoration
TLDR
The proposed framework explicitly learn the inherent pixel correspondence between stereo views and restores stereo image with the cross-view information at image and feature level with the superiority of the proposed framework on various stereo image restoration tasks.
A Stereo Attention Module for Stereo Image Super-Resolution
TLDR
Using SAM, the generic stereo attention module (SAM) is proposed to extend arbitrary SISR networks to stereo images and can exploit cross-view information while maintaining the superiority of intra-View information exploitation, resulting in notable performance gain to SisR networks.
Resolution Enhancement in Multi-Image Stereo
TLDR
This paper proposes an integrated approach to estimate the HR depth and the SR image from multiple LR stereo observations and demonstrates the efficacy of the proposed method in not only being able to bring out image details but also in enhancing theHR depth over its LR counterpart.
Learning Parallax Attention for Stereo Image Super-Resolution
TLDR
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.
Stereoscopic Image Super-Resolution with Stereo Consistent Feature
TLDR
A self and parallax attention mechanism (SPAM) to aggregate the information from its own image and the counterpart stereo image simultaneously, thus reconstructing high-quality stereoscopic SR image pairs and demonstrating the superiority of this method over state-of-the-art SR methods.
Parallax Attention for Unsupervised Stereo Correspondence Learning
TLDR
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.
Deep Bilateral Learning for Stereo Image Super-Resolution
TLDR
This letter uses a parallax-attention module to incorporate information from left and right views to learn content-aware bilateral filters, which are used to recover missing details at different spatial locations while preserving stereo consistency in a bilateral stereo super-resolution network.
Learning for Disparity Estimation Through Feature Constancy
TLDR
This paper proposes a network architecture to incorporate all steps of stereo matching, including matching cost calculation, matching cost aggregation, disparity calculation, and disparity refinement, which achieves the state-of-the-art performance on the KITTI 2012 and KittI 2015 benchmarks while maintaining a very fast running time.
Deep Stereoscopic Image Super-Resolution via Interaction Module
TLDR
An interaction module-based stereoscopic image super-resolution network (IMSSRnet) is proposed to effectively utilize the correlation information in stereoscopic images to achieve promising performance and outperforms the state-of-the-art methods.
Combining multi-view stereo and super resolution in a unified framework
TLDR
A novel method to solve two problems together by optimizing a unified energy functional by considering the consistency between high resolution images is considered along with consideration to the consistency of high-resolution and low-resolution image pair with the same viewpoint.
...
1
2
3
4
5
...