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

arXiv: https://arxiv.org/abs/2106.00985 · HTML: https://mlsanity.com/paper/2106.00985/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 40 references that are in the map.
- First posted on arXiv 2 Jun 2021.

## Builds on (most cited first, 19 of 19)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Enhanced Deep Residual Networks for Single Image Super-Resolution](https://mlsanity.com/paper/1707.02921/) (2017)
- [Accurate Image Super-Resolution Using Very Deep Convolutional Networks](https://mlsanity.com/paper/1511.04587/) (2015)
- [A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation](https://mlsanity.com/paper/1512.02134/) (2015)
- [Multi-Task Learning as Multi-Objective Optimization](https://mlsanity.com/paper/1810.04650/) (2018)
- [Residual Dense Network for Image Super-Resolution](https://mlsanity.com/paper/1802.08797/) (2018)
- [Pyramid Stereo Matching Network](https://mlsanity.com/paper/1803.08669/) (2018)
- [Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching](https://mlsanity.com/paper/1912.06378/) (2019)
- [End-to-End Learning of Geometry and Context for Deep Stereo Regression](https://mlsanity.com/paper/1703.04309/) (2017)
- [GA-Net: Guided Aggregation Net for End-to-end Stereo Matching](https://mlsanity.com/paper/1904.06587/) (2019)
- [AANet: Adaptive Aggregation Network for Efficient Stereo Matching](https://mlsanity.com/paper/2004.09548/) (2020)
- [Feedback Network for Image Super-Resolution](https://mlsanity.com/paper/1903.09814/) (2019)
- [StereoNet: Guided Hierarchical Refinement for Real-Time Edge-Aware Depth Prediction](https://mlsanity.com/paper/1807.08865/) (2018)
- [SegStereo: Exploiting Semantic Information for Disparity Estimation](https://mlsanity.com/paper/1807.11699/) (2018)
- [Learning Parallax Attention for Stereo Image Super-Resolution](https://mlsanity.com/paper/1903.05784/) (2019)
- [Parallax Attention for Unsupervised Stereo Correspondence Learning](https://mlsanity.com/paper/2009.08250/) (2020)
- [Symmetric Parallax Attention for Stereo Image Super-Resolution](https://mlsanity.com/paper/2011.03802/) (2020)
- [StereoDRNet: Dilated Residual Stereo Net](https://mlsanity.com/paper/1904.02251/) (2019)
- [Progressive Fusion for Unsupervised Binocular Depth Estimation using Cycled Networks](https://mlsanity.com/paper/1909.07667/) (2019)

## Built on by (most cited first, 21 of 21)

- [NAFSSR: Stereo Image Super-Resolution Using NAFNet](https://mlsanity.com/paper/2204.08714/) (2022)
- [SwinFIR: Revisiting the SwinIR with Fast Fourier Convolution and Improved Training for Image Super-Resolution](https://mlsanity.com/paper/2208.11247/) (2022)
- [Efficient Real-world Image Super-Resolution Via Adaptive Directional Gradient Convolution](https://mlsanity.com/paper/2405.07023/) (2024)
- [Fine-structure Preserved Real-world Image Super-resolution via Transfer VAE Training](https://mlsanity.com/paper/2507.20291/) (2025)
- [A Systematic Survey of Deep Learning-based Single-Image Super-Resolution](https://mlsanity.com/paper/2109.14335/) (2021)
- [NTIRE 2022 Challenge on Stereo Image Super-Resolution: Methods and Results](https://mlsanity.com/paper/2204.09197/) (2022)
- [SwinFSR: Stereo Image Super-Resolution using SwinIR and Frequency Domain Knowledge](https://mlsanity.com/paper/2304.12556/) (2023)
- [Hybrid Transformer and CNN Attention Network for Stereo Image Super-resolution](https://mlsanity.com/paper/2305.05177/) (2023)
- [NTIRE 2023 Challenge on Light Field Image Super-Resolution: Dataset, Methods and Results](https://mlsanity.com/paper/2304.10415/) (2023)
- [PFT-SSR: Parallax Fusion Transformer for Stereo Image Super-Resolution](https://mlsanity.com/paper/2303.13807/) (2023)
- [Cross-View Hierarchy Network for Stereo Image Super-Resolution](https://mlsanity.com/paper/2304.06236/) (2023)
- [Learning Accurate and Enriched Features for Stereo Image Super-Resolution](https://mlsanity.com/paper/2406.16001/) (2024)
- [StereoINR: Cross-View Geometry Consistent Stereo Super Resolution with Implicit Neural Representation](https://mlsanity.com/paper/2505.05509/) (2025)
- [Stereo Image Rain Removal via Dual-View Mutual Attention](https://mlsanity.com/paper/2211.10104/) (2022)
- [Toward Real World Stereo Image Super-Resolution via Hybrid Degradation Model and Discriminator for Implied Stereo Image Information](https://mlsanity.com/paper/2312.07934/) (2023)
- [Multi-Level Feature Fusion Network for Lightweight Stereo Image Super-Resolution](https://mlsanity.com/paper/2405.05497/) (2024)
- [Deep Learning Empowered Super-Resolution: A Comprehensive Survey and Future Prospects](https://mlsanity.com/paper/2509.22692/) (2025)
- [NAFRSSR: a Lightweight Recursive Network for Efficient Stereo Image Super-Resolution](https://mlsanity.com/paper/2405.08423/) (2024)
- [ASteISR: Adapting Single Image Super-resolution Pre-trained Model for Efficient Stereo Image Super-resolution](https://mlsanity.com/paper/2407.03598/) (2024)
- [NTIRE 2024 Challenge on Stereo Image Super-Resolution: Methods and Results](https://mlsanity.com/paper/2409.16947/) (2024)
- [Multi-scale interaction network for stereo image super-resolution](https://mlsanity.com/paper/2605.21913/) (2026)

## Abstract (arXiv)

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 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. Specifically, the SSRDE-FNet is composed of two dual recursive sub-networks for left and right views. Besides the cross-view information exploitation in the low-resolution (LR) space, HR representations produced by the SR process are utilized to perform HR disparity estimation with higher accuracy, through which the HR features can be aggregated to generate a finer SR result. Afterward, the proposed HR Disparity Information Feedback (HRDIF) mechanism delivers information carried by HR disparity back to previous layers to further refine the SR image reconstruction. Extensive experiments demonstrate the effectiveness and advancement of SSRDE-FNet.