.png){kind=icon}
.png){kind=icon}
Return
CNDesc: Cross Normalization for Local Descriptors Learning
.png){kind=icon}
PRE
AI
DOI：10.1109/TMM.2022.3169331.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
For a long time, the local descriptors learning benefited from the use of L2 normalization, which projects the descriptor space onto the hypersphere. However, there is no free lunch in the world. Although hypersphere description space stabilizes the optimization and improves the repeatability of the descriptors, it causes the descriptors to have a denser distribution, which reduces the discrimination between descriptors and leads to some incorrect matches. To alleviate this problem, we propose the learnable cross normalization technology as an alternative to L2 normalization, which can achieve a consistent improvement in several of the current popular local descriptors. In addition, we propose an ER-Backbone that can efficiently reuse features in descriptors extraction and an IDC Loss that can provide an image-level description space distribution consistency constraint to further stimulate the performance of the local descriptors. Based on the above innovations, we provide a novel local descriptors extraction method named CNDesc. We perform experiments on image matching, homography estimation, 3D reconstruction, and visual localization tasks, and the results demonstrate that our CNDesc surpasses the current state-of-the-art local descriptors. Our code is available at https:// github.com/ vignywang/ CNDesc.
Keywords:
Feature extraction
Visualization
Task analysis
Three-dimensional displays
Standards
Optimization
Training
Local descriptors
cross normalization
efficient feature reuse backbone
image-level distribution consistent loss
Journal
IF:
9.7
Papers:
4.5K
Citations:
2.4W