# UWStereo: A Large Synthetic Dataset for Underwater Stereo Matching

arXiv: https://arxiv.org/abs/2409.01782 · HTML: https://mlsanity.com/paper/2409.01782/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 65 references that are in the map.
- First posted on arXiv 3 Sep 2024.

## Builds on (most cited first, 30 of 40)

- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [CARLA: An Open Urban Driving Simulator](https://mlsanity.com/paper/1711.03938/) (2017)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [MUSIQ: Multi-scale Image Quality Transformer](https://mlsanity.com/paper/2108.05997/) (2021)
- [LoFTR: Detector-Free Local Feature Matching with Transformers](https://mlsanity.com/paper/2104.00680/) (2021)
- [A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation](https://mlsanity.com/paper/1512.02134/) (2015)
- [Pyramid Stereo Matching Network](https://mlsanity.com/paper/1803.08669/) (2018)
- [RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matching](https://mlsanity.com/paper/2109.07547/) (2021)
- [An Underwater Image Enhancement Benchmark Dataset and Beyond](https://mlsanity.com/paper/1901.05495/) (2019)
- [GA-Net: Guided Aggregation Net for End-to-end Stereo Matching](https://mlsanity.com/paper/1904.06587/) (2019)
- [Group-wise Correlation Stereo Network](https://mlsanity.com/paper/1903.04025/) (2019)
- [AANet: Adaptive Aggregation Network for Efficient Stereo Matching](https://mlsanity.com/paper/2004.09548/) (2020)
- [Practical Stereo Matching via Cascaded Recurrent Network with Adaptive Correlation](https://mlsanity.com/paper/2203.11483/) (2022)
- [Iterative Geometry Encoding Volume for Stereo Matching](https://mlsanity.com/paper/2303.06615/) (2023)
- [Co-SLAM: Joint Coordinate and Sparse Parametric Encodings for Neural Real-Time SLAM](https://mlsanity.com/paper/2304.14377/) (2023)
- [Hierarchical Neural Architecture Search for Deep Stereo Matching](https://mlsanity.com/paper/2010.13501/) (2020)
- [CroCo v2: Improved Cross-view Completion Pre-training for Stereo Matching and Optical Flow](https://mlsanity.com/paper/2211.10408/) (2022)
- [Stereo Matching by Training a Convolutional Neural Network to Compare Image Patches](https://mlsanity.com/paper/1510.05970/) (2015)
- [Attention Concatenation Volume for Accurate and Efficient Stereo Matching](https://mlsanity.com/paper/2203.02146/) (2022)
- [WaterGAN: Unsupervised Generative Network to Enable Real-time Color Correction of Monocular Underwater Images](https://mlsanity.com/paper/1702.07392/) (2017)
- [Domain-invariant Stereo Matching Networks](https://mlsanity.com/paper/1911.13287/) (2019)
- [Selective-Stereo: Adaptive Frequency Information Selection for Stereo Matching](https://mlsanity.com/paper/2403.00486/) (2024)
- [Semantic Segmentation of Underwater Imagery: Dataset and Benchmark](https://mlsanity.com/paper/2004.01241/) (2020)
- [Underwater Single Image Color Restoration Using Haze-Lines and a New Quantitative Dataset](https://mlsanity.com/paper/1811.01343/) (2018)
- [SeaThru-NeRF: Neural Radiance Fields in Scattering Media](https://mlsanity.com/paper/2304.07743/) (2023)
- [PCW-Net: Pyramid Combination and Warping Cost Volume for Stereo Matching](https://mlsanity.com/paper/2006.12797/) (2020)
- [VolRecon: Volume Rendering of Signed Ray Distance Functions for Generalizable Multi-View Reconstruction](https://mlsanity.com/paper/2212.08067/) (2022)
- [IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo](https://mlsanity.com/paper/2112.05126/) (2021)
- [MoCha-Stereo: Motif Channel Attention Network for Stereo Matching](https://mlsanity.com/paper/2404.06842/) (2024)
- [NeRF-Supervised Deep Stereo](https://mlsanity.com/paper/2303.17603/) (2023)

## Built on by (most cited first, 7 of 7)

- [StereoAdapter: Adapting Stereo Depth Estimation to Underwater Scenes](https://mlsanity.com/paper/2509.16415/) (2025)
- [AquaStereo: Enabling Underwater Stereo Matching via Depth-Conditioned Diffusion and Geometry Self-Distillation](https://mlsanity.com/paper/2607.04303/) (2026)
- [Wat3R: Underwater 3D Geometry Learning without Annotations](https://mlsanity.com/paper/2607.08772/) (2026)
- [StereoAdapter-2: Globally Structure-Consistent Underwater Stereo Depth Estimation](https://mlsanity.com/paper/2602.16915/) (2026)
- [M3D-Stereo: A Multiple-Medium and Multiple-Degradation Dataset for Stereo Image Restoration](https://mlsanity.com/paper/2604.12917/) (2026)
- [LinStereo: Linear-Complexity Global Attention for Multi-Scale Iterative Stereo Matching](https://mlsanity.com/paper/2606.25437/) (2026)
- [WaterGen: Decoupling Scene and Medium in Underwater Image Generation](https://mlsanity.com/paper/2606.31147/) (2026)

## Abstract (arXiv)

Despite recent advances in stereo matching, the extension to intricate underwater settings remains unexplored, primarily owing to: 1) the reduced visibility, low contrast, and other adverse effects of underwater images; 2) the difficulty in obtaining ground truth data for training deep learning models, i.e. simultaneously capturing an image and estimating its corresponding pixel-wise depth information in underwater environments. To enable further advance in underwater stereo matching, we introduce a large synthetic dataset called UWStereo. Our dataset includes 29,568 synthetic stereo image pairs with dense and accurate disparity annotations for left view. We design four distinct underwater scenes filled with diverse objects such as corals, ships and robots. We also induce additional variations in camera model, lighting, and environmental effects. In comparison with existing underwater datasets, UWStereo is superior in terms of scale, variation, annotation, and photo-realistic image quality. To substantiate the efficacy of the UWStereo dataset, we undertake a comprehensive evaluation compared with nine state-of-the-art algorithms as benchmarks. The results indicate that current models still struggle to generalize to new domains. Hence, we design a new strategy that learns to reconstruct cross domain masked images before stereo matching training and integrate a cross view attention enhancement module that aggregates long-range content information to enhance the generalization ability.