ALIKED: A Lighter Keypoint and Descriptor Extraction Network via Deformable Transformation

Authors:
Top Cited Papers
Publisher website
Google Scholar
Abstract
Image keypoints and descriptors play a crucial role in many visual measurement tasks. In recent years, deep neural networks have been widely used to improve the performance of keypoint and descriptor extraction. However, the conventional convolution operations do not provide the geometric invariance required for the descriptor. To address this issue, we propose the Sparse Deformable Descriptor Head (SDDH), which learns the deformable positions of supporting features for each keypoint and constructs deformable descriptors. Furthermore, SDDH extracts descriptors at sparse keypoints instead of a dense descriptor map, which enables efficient extraction of descriptors with strong expressiveness. In addition, we relax the neural reprojection error (NRE) loss from dense to sparse to train the extracted sparse descriptors. Experimental results show that the proposed network is both efficient and powerful in various visual measurement tasks, including image matching, 3D reconstruction, and visual relocalization.
Funding Information
  • National Natural Science Foundation of China (51975029, U1909215)
  • Agency for Science, Technology and Research of Singapore under the Robotics Horizontal Technology Coordinating Office Project (C221518005)
  • Key Research and Development Program of Zhejiang Province (2021C03050)
  • Macao Science and Technology Development Fund (0022/2019/AKP)
  • National Natural Science Foundation of China (61620106012, 61573048)