Water Reflection Detection Using Symmetric Attention
2026-07-12 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors address the problem that computers often mistake reflections in water for real objects, which confuses tasks like object detection. They propose a new system called SAWRD-Net that uses special math operations to recognize mirror and rotational symmetries in images of water. This system highlights reflection areas and directly finds the reflection axis, improving accuracy. Tested on a large dataset, their method detects water reflections more reliably than previous approaches.
water reflectiondeep learningsymmetrydihedral group convolutionsemantic segmentationobject detectionprincipal component analysisreflection axislow-rank decompositionattention mechanism
Authors
Shuxuan Yao, Chengjia Wang, Jianyuan Sun, Junyu Dong, Xinghui Dong
Abstract
Reflections of water pose a significant challenge for computer vision systems, as standard deep learning models frequently confuse objects with their mirror images, producing spurious false positives and negatives in tasks such as object detection and semantic segmentation. As a result, detecting reflection axes in natural-water scenes is pivotal for reliable object detection and scene understanding. To mitigate this issue, we leverage the intrinsic imperfect reflective symmetry of water and introduce a Symmetry-Aware Water Reflection Detection Network, namely, SAWRD-Net, that couples dihedral group-equivariant convolutions with a matrix-decomposition decoder in an end-to-end framework. First, dihedral group convolutional layers extract geometry-consistent feature maps that explicitly encode both rotational and mirror symmetries. A Multi-scale Reflection Equivariant block then aggregates features across scales and employs a symmetric-attention mechanism to highlight reflection-relevant regions. The proposed matrix-decomposition decoder factorizes high-dimensional features into compact low-rank parameter and confidence spaces, after which the network directly regresses keypoints on the reflection axis. Then a robust principal component analysis fits the final axis. Evaluated on the largest available water reflection scene data set, SAWRD-Net achieves a true-positive rate of 0.890 against human annotations, outperforming all existing water reflection detectors.