In recent years, learning-based feature detection and matching have outperformed manually-designed methods in in-air cases. However, it is challenging to learn the features in the underwater scenario due to the absence of annotated underwater datasets. This paper proposes a cross-modal knowledge distillation framework for training an underwater feature detection and matching network (UFEN). In particular, we use in-air RGBD data to generate synthetic underwater images based on a physical underwater imaging formation model and employ these as the medium to distil knowledge from a teacher model SuperPoint pretrained on in-air images. We embed UFEN into the ORB-SLAM3 framework to replace the ORB feature by introducing an additional binarization layer. To test the effectiveness of our method, we built a new underwater dataset with groundtruth measurements named EASI (https://github.com/Jinghe-mel/UFEN-SLAM), recorded in an indoor water tank for different turbidity levels. The experimental results on the existing dataset and our new dataset demonstrate the effectiveness of our method.

翻译：近年来，基于学习的特征检测与匹配在空气场景中已超越手工设计方法。然而，由于缺乏带标注的水下数据集，在水下场景中学习特征具有挑战性。本文提出一种跨模态知识蒸馏框架，用于训练水下特征检测与匹配网络（UFEN）。具体而言，我们利用空气RGBD数据，基于物理水下成像模型生成合成水下图像，并以此作为媒介，从预训练于空气图像的教师模型SuperPoint中蒸馏知识。通过引入额外二值化层，我们将UFEN嵌入ORB-SLAM3框架中替代ORB特征。为验证方法有效性，我们构建了名为EASI（https://github.com/Jinghe-mel/UFEN-SLAM）的新水下数据集，该数据集包含不同浊度水平下室内水槽的真实测量数据。在现有数据集及新数据集上的实验结果均证明了我们方法的有效性。