# Stereo Matching Based on Visual Sensitive Information

arXiv: https://arxiv.org/abs/2105.10831 · HTML: https://mlsanity.com/paper/2105.10831/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 25 references that are in the map.
- First posted on arXiv 23 May 2021.

## Builds on (most cited first, 9 of 9)

- [Multi-label Cloud Segmentation Using a Deep Network](https://mlsanity.com/paper/1903.06562/) (2019)
- [Cross-Scale Cost Aggregation for Stereo Matching](https://mlsanity.com/paper/1403.0316/) (2014)
- [An Advert Creation System for 3D Product Placements](https://mlsanity.com/paper/2006.15131/) (2020)
- [Estimation of solar irradiance using ground-based whole sky imagers](https://mlsanity.com/paper/1606.02546/) (2016)
- [Detecting Rainfall Onset Using Sky Images](https://mlsanity.com/paper/1610.06667/) (2016)
- [An Advert Creation System for Next-Gen Publicity](https://mlsanity.com/paper/1808.00163/) (2018)
- [ADNet: A Deep Network for Detecting Adverts](https://mlsanity.com/paper/1811.04115/) (2018)
- [Localizing Adverts in Outdoor Scenes](https://mlsanity.com/paper/1905.02106/) (2019)
- [Analyzing Cloud Optical Properties Using Sky Cameras](https://mlsanity.com/paper/1708.08995/) (2017)

## Built on by (most cited first, 6 of 6)

- [CPDR: Towards Highly-Efficient Salient Object Detection via Crossed Post-decoder Refinement](https://mlsanity.com/paper/2501.06441/) (2025)
- [DDUNet: Dual Dynamic U-Net for Highly-Efficient Cloud Segmentation](https://mlsanity.com/paper/2501.15385/) (2025)
- [UCloudNet: A Residual U-Net with Deep Supervision for Cloud Image Segmentation](https://mlsanity.com/paper/2501.06440/) (2025)
- [CP2M: Clustered-Patch-Mixed Mosaic Augmentation for Aerial Image Segmentation](https://mlsanity.com/paper/2501.15389/) (2025)
- [TrafficKAN-GCN: Graph Convolutional-based Kolmogorov-Arnold Network for Traffic Flow Optimization](https://mlsanity.com/paper/2503.03276/) (2025)
- [Segregation and Context Aggregation Network for Real-time Cloud Segmentation](https://mlsanity.com/paper/2504.14178/) (2025)

## Abstract (arXiv)

The area of computer vision is one of the most discussed topics amongst many scholars, and stereo matching is its most important sub fields. After the parallax map is transformed into a depth map, it can be applied to many intelligent fields. In this paper, a stereo matching algorithm based on visual sensitive information is proposed by using standard images from Middlebury dataset. Aiming at the limitation of traditional stereo matching algorithms regarding the cost window, a cost aggregation algorithm based on the dynamic window is proposed, and the disparity image is optimized by using left and right consistency detection to further reduce the error matching rate. The experimental results show that the proposed algorithm can effectively enhance the stereo matching effect of the image providing significant improvement in accuracy as compared with the classical census algorithm. The proposed model code, dataset, and experimental results are available at https://github.com/WangHewei16/Stereo-Matching.