# Parallax Attention for Unsupervised Stereo Correspondence Learning

arXiv: https://arxiv.org/abs/2009.08250 · HTML: https://mlsanity.com/paper/2009.08250/

## Key facts

- Cited by 39 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Sep 2020.

## Built on by (most cited first, 30 of 39)

- [Accurate and Efficient Stereo Matching via Attention Concatenation Volume](https://mlsanity.com/paper/2209.12699/) (2022)
- [Bilateral Grid Learning for Stereo Matching Networks](https://mlsanity.com/paper/2101.01601/) (2021)
- [Decoupling Makes Weakly Supervised Local Feature Better](https://mlsanity.com/paper/2201.02861/) (2022)
- [Visible-Thermal Tiny Object Detection: A Benchmark Dataset and Baselines](https://mlsanity.com/paper/2406.14482/) (2024)
- [Feedback Network for Mutually Boosted Stereo Image Super-Resolution and Disparity Estimation](https://mlsanity.com/paper/2106.00985/) (2021)
- [Learning Non-Local Spatial-Angular Correlation for Light Field Image Super-Resolution](https://mlsanity.com/paper/2302.08058/) (2023)
- [A Systematic Survey of Deep Learning-based Single-Image Super-Resolution](https://mlsanity.com/paper/2109.14335/) (2021)
- [Stereo Matching by Self-supervision of Multiscopic Vision](https://mlsanity.com/paper/2104.04170/) (2021)
- [ChiTransformer:Towards Reliable Stereo from Cues](https://mlsanity.com/paper/2203.04554/) (2022)
- [NTIRE 2022 Challenge on Stereo Image Super-Resolution: Methods and Results](https://mlsanity.com/paper/2204.09197/) (2022)
- [Local Motion and Contrast Priors Driven Deep Network for Infrared Small Target Super-Resolution](https://mlsanity.com/paper/2201.01014/) (2022)
- [Two-in-One Depth: Bridging the Gap Between Monocular and Binocular Self-supervised Depth Estimation](https://mlsanity.com/paper/2309.00933/) (2023)
- [Dense Dual-Attention Network for Light Field Image Super-Resolution](https://mlsanity.com/paper/2110.12114/) (2021)
- [Invertible Attention](https://mlsanity.com/paper/2106.09003/) (2021)
- [Degradation-agnostic Correspondence from Resolution-asymmetric Stereo](https://mlsanity.com/paper/2204.01429/) (2022)
- [Monocular Road Planar Parallax Estimation](https://mlsanity.com/paper/2111.11089/) (2021)
- [Depth Estimation by Combining Binocular Stereo and Monocular Structured-Light](https://mlsanity.com/paper/2203.10493/) (2022)
- [Cross-View Hierarchy Network for Stereo Image Super-Resolution](https://mlsanity.com/paper/2304.06236/) (2023)
- [StereoINR: Cross-View Geometry Consistent Stereo Super Resolution with Implicit Neural Representation](https://mlsanity.com/paper/2505.05509/) (2025)
- [DMS:Diffusion-Based Multi-Baseline Stereo Generation for Improving Self-Supervised Depth Estimation](https://mlsanity.com/paper/2508.13091/) (2025)
- [RoSe: Robust Self-supervised Stereo Matching under Adverse Weather Conditions](https://mlsanity.com/paper/2509.19165/) (2025)
- [SMFormer: Empowering Self-supervised Stereo Matching via Foundation Models and Data Augmentation](https://mlsanity.com/paper/2604.10218/) (2026)
- [FCDSN-DC: An Accurate and Lightweight Convolutional Neural Network for Stereo Estimation with Depth Completion](https://mlsanity.com/paper/2209.06525/) (2022)
- [IFAST: Weakly Supervised Interpretable Face Anti-spoofing from Single-shot Binocular NIR Images](https://mlsanity.com/paper/2309.17399/) (2023)
- [Low-light Stereo Image Enhancement and De-noising in the Low-frequency Information Enhanced Image Space](https://mlsanity.com/paper/2401.07753/) (2024)
- [Unsupervised Stereo Matching Network For VHR Remote Sensing Images Based On Error Prediction](https://mlsanity.com/paper/2408.07419/) (2024)
- [Heterogeneous Graph Transformer for Multiple Tiny Object Tracking in RGB-T Videos](https://mlsanity.com/paper/2412.10861/) (2024)
- [Color Mismatches in Stereoscopic Video: Real-World Dataset and Deep Correction Method](https://mlsanity.com/paper/2303.06657/) (2023)
- [Saliency-aware Stereoscopic Video Retargeting](https://mlsanity.com/paper/2304.08852/) (2023)
- [SEGSRNet for Stereo-Endoscopic Image Super-Resolution and Surgical Instrument Segmentation](https://mlsanity.com/paper/2404.13330/) (2024)

## Abstract (arXiv)

Stereo image pairs encode 3D scene cues into stereo correspondences between the left and right images. To exploit 3D cues within stereo images, recent CNN based methods commonly use cost volume techniques to capture stereo correspondence over large disparities. However, since disparities can vary significantly for stereo cameras with different baselines, focal lengths and resolutions, the fixed maximum disparity used in cost volume techniques hinders them to handle different stereo image pairs with large disparity variations. In this paper, we propose a generic parallax-attention mechanism (PAM) to capture stereo correspondence regardless of disparity variations. Our PAM integrates epipolar constraints with attention mechanism to calculate feature similarities along the epipolar line to capture stereo correspondence. Based on our PAM, we propose a parallax-attention stereo matching network (PASMnet) and a parallax-attention stereo image super-resolution network (PASSRnet) for stereo matching and stereo image super-resolution tasks. Moreover, we introduce a new and large-scale dataset named Flickr1024 for stereo image super-resolution. Experimental results show that our PAM is generic and can effectively learn stereo correspondence under large disparity variations in an unsupervised manner. Comparative results show that our PASMnet and PASSRnet achieve the state-of-the-art performance.