发表机构
State Key Laboratory of Physical Oceanography and the Faculty of Information Science and Engineering, Ocean University of China; School of Mathematical and Computer Sciences, Heriot-Watt University; School of Computer Science and Informatics, De Montfort University（中国海洋大学物理海洋学国家重点实验室和信息科学与工程学院; 赫瑞瓦特大学数学与计算机科学学院; 德蒙福特大学计算机科学与信息学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究水反射检测难题，提出SAWRD-Net，结合二面体群等变卷积与矩阵分解解码器，利用水反射对称性不完善特性，在最大水反射场景数据集上取得0.890真阳性率，优于现有探测器。
AI 中文摘要
水的反射给计算机视觉系统带来重大挑战，标准深度学习模型常将物体与镜像混淆。检测自然水景中的反射轴对可靠目标检测和场景理解至关重要。为此，我们利用水固有的反射对称性不完善，引入对称感知水反射检测网络SAWRD-Net，将二面体群等变卷积与矩阵分解解码器结合在端到端框架中。实验表明，SAWRD-Net在最大可用水反射场景数据集上，相对于人工标注的真阳性率达到0.890，优于所有现有水反射探测器。
英文摘要
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.
