GeoDesc：通过集成几何约束学习局部描述符
GeoDesc: Learning Local Descriptors by Integrating Geometry Constraints
摘要：
基于卷积神经网络（CNN）学习的局部描述符在基于块的基准测试中取得了显着的改进，但在最近的基于图像的3D重建基准测试中没有表现出较强的泛化能力。在本文中，我们通过提出一种新的局部描述符学习方法来减轻这种限制，该方法集成了多视图重建的几何约束，这有利于学习过程中的数据生成，数据采样和损失计算。我们将建议的描述符称为GeoDesc，并在各种大规模基准测试中展示了其卓越的性能，特别是在具有挑战性的重建任务中取得了巨大的成功。此外，我们提供了在运动恢复结构（SfM）管道中实际集成学习描述符的指导方针，显示了GeoDesc在准确性和效率之间为3D重建任务提供的良好权衡。
英文摘要：
Learned local descriptors based on Convolutional Neural Networks (CNNs) have achieved significant improvements on patch-based benchmarks, whereas not having demonstrated strong generalization ability on recent benchmarks of image-based 3D reconstruction. In this paper, we mitigate this limitation by proposing a novel local descriptor learning approach that integrates geometry constraints from multi-view reconstructions, which benefits the learning process in terms of data generation, data sampling and loss computation. We refer to the proposed descriptor as GeoDesc, and demonstrate its superior performance on various large-scale benchmarks, and in particular show its great success on challenging reconstruction tasks. Moreover, we provide guidelines towards practical integration of learned descriptors in Structure-from-Motion (SfM) pipelines, showing the good trade-off that GeoDesc delivers to 3D reconstruction tasks between accuracy and efficiency.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
