论文标题
共享耦合桥，用于弱监督的本地功能学习
Shared Coupling-bridge for Weakly Supervised Local Feature Learning
论文作者
论文摘要
通常认为稀疏的局部特征提取在典型的视觉任务中具有重要意义，例如同时定位和映射，图像匹配和3D重建。目前，它仍然存在一些需要进一步改进的缺陷，主要包括提取的本地描述符的歧视能力，检测到的关键点的本地化准确性以及本地特征学习的效率。本文着重于通过相机姿势监督促进当前流行的稀疏本地功能学习。因此，它对共享的耦合桥方案进行了相关性，具有四个轻巧但有效的改进，以进行弱监督的本地特征（SCFEAT）学习。 It mainly contains: i) the \emph{Feature-Fusion-ResUNet Backbone} (F2R-Backbone) for local descriptors learning, ii) a shared coupling-bridge normalization to improve the decoupling training of description network and detection network, iii) an improved detection network with peakiness measurement to detect keypoints and iv) the fundamental matrix error as a reward factor to further optimize feature detection 训练。广泛的实验证明我们的SCFEAT改进是有效的。它通常可以在经典图像匹配和视觉定位上获得最新的性能。就3D重建而言，它仍然可以取得竞争成果。对于共享和通信，我们的源代码可在https://github.com/sunjiayuanro/scfeat.git上找到。
Sparse local feature extraction is usually believed to be of important significance in typical vision tasks such as simultaneous localization and mapping, image matching and 3D reconstruction. At present, it still has some deficiencies needing further improvement, mainly including the discrimination power of extracted local descriptors, the localization accuracy of detected keypoints, and the efficiency of local feature learning. This paper focuses on promoting the currently popular sparse local feature learning with camera pose supervision. Therefore, it pertinently proposes a Shared Coupling-bridge scheme with four light-weight yet effective improvements for weakly-supervised local feature (SCFeat) learning. It mainly contains: i) the \emph{Feature-Fusion-ResUNet Backbone} (F2R-Backbone) for local descriptors learning, ii) a shared coupling-bridge normalization to improve the decoupling training of description network and detection network, iii) an improved detection network with peakiness measurement to detect keypoints and iv) the fundamental matrix error as a reward factor to further optimize feature detection training. Extensive experiments prove that our SCFeat improvement is effective. It could often obtain a state-of-the-art performance on classic image matching and visual localization. In terms of 3D reconstruction, it could still achieve competitive results. For sharing and communication, our source codes are available at https://github.com/sunjiayuanro/SCFeat.git.
