Journal
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
Volume 72, Issue -, Pages -Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TIM.2023.3271000
Keywords
Feature extraction; Visualization; Convolution; Head; Task analysis; Neural networks; Training; Deformable; descriptor; image matching; keypoint; local feature
Ask authors/readers for more resources
Image keypoints and descriptors are important for visual measurement tasks. Deep neural networks have been used to improve their performance. However, conventional convolution operations lack the required geometric invariance for the descriptor. To address this, we propose the sparse deformable descriptor head (SDDH), which learns deformable positions of features for each keypoint. SDDH extracts descriptors at sparse keypoints, enabling efficient extraction with strong expressiveness.
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, 3-D reconstruction, and visual relocalization.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available