# Stereo Waterdrop Removal with Row-wise Dilated Attention

arXiv: https://arxiv.org/abs/2108.03457 · HTML: https://mlsanity.com/paper/2108.03457/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 46 references that are in the map.
- First posted on arXiv 7 Aug 2021.

## Builds on (most cited first, 20 of 20)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [Pyramid Stereo Matching Network](https://mlsanity.com/paper/1803.08669/) (2018)
- [GA-Net: Guided Aggregation Net for End-to-end Stereo Matching](https://mlsanity.com/paper/1904.06587/) (2019)
- [Photographic Image Synthesis with Cascaded Refinement Networks](https://mlsanity.com/paper/1707.09405/) (2017)
- [Attentive Generative Adversarial Network for Raindrop Removal from a Single Image](https://mlsanity.com/paper/1711.10098/) (2017)
- [AANet: Adaptive Aggregation Network for Efficient Stereo Matching](https://mlsanity.com/paper/2004.09548/) (2020)
- [Hierarchical Deep Stereo Matching on High-resolution Images](https://mlsanity.com/paper/1912.06704/) (2019)
- [Polarized Reflection Removal with Perfect Alignment in the Wild](https://mlsanity.com/paper/2003.12789/) (2020)
- [Learning Parallax Attention for Stereo Image Super-Resolution](https://mlsanity.com/paper/1903.05784/) (2019)
- [Learning to See Through Obstructions](https://mlsanity.com/paper/2004.01180/) (2020)
- [DAVANet: Stereo Deblurring with View Aggregation](https://mlsanity.com/paper/1904.05065/) (2019)
- [Stereoscopic Neural Style Transfer](https://mlsanity.com/paper/1802.10591/) (2018)
- [Neural Stereoscopic Image Style Transfer](https://mlsanity.com/paper/1802.09985/) (2018)

## Built on by (most cited first, 5 of 5)

- [Video Waterdrop Removal via Spatio-Temporal Fusion in Driving Scenes](https://mlsanity.com/paper/2302.05916/) (2023)
- [Dual-Pixel Raindrop Removal](https://mlsanity.com/paper/2210.13321/) (2022)
- [Stereo Image Rain Removal via Dual-View Mutual Attention](https://mlsanity.com/paper/2211.10104/) (2022)
- [SNNSIR: A Simple Spiking Neural Network for Stereo Image Restoration](https://mlsanity.com/paper/2508.12271/) (2025)
- [HaRP: High Dynamic Range Photosequencing through Dual Reversed Shutter Scanning](https://mlsanity.com/paper/2609.28439/) (2026)

## Abstract (arXiv)

Existing vision systems for autonomous driving or robots are sensitive to waterdrops adhered to windows or camera lenses. Most recent waterdrop removal approaches take a single image as input and often fail to recover the missing content behind waterdrops faithfully. Thus, we propose a learning-based model for waterdrop removal with stereo images. To better detect and remove waterdrops from stereo images, we propose a novel row-wise dilated attention module to enlarge attention's receptive field for effective information propagation between the two stereo images. In addition, we propose an attention consistency loss between the ground-truth disparity map and attention scores to enhance the left-right consistency in stereo images. Because of related datasets' unavailability, we collect a real-world dataset that contains stereo images with and without waterdrops. Extensive experiments on our dataset suggest that our model outperforms state-of-the-art methods both quantitatively and qualitatively. Our source code and the stereo waterdrop dataset are available at hrefhttps://github.com/VivianSZF/Stereo-Waterdrop-Removalhttps://github.com/VivianSZF/Stereo-Waterdrop-Removal