DRKF: Distilled Rotated Kernel Fusion for Efficient Rotation Invariant Descriptors in Local Feature Matching
Ranran Huang,Jiancheng Cai,Chao Li,Zhuoyuan Wu,Xinmin Liu,Zhenhua Chai,Ranran Huang,Jiancheng Cai,Chao Li,Zhuoyuan Wu,Xinmin Liu,Zhenhua Chai
The performance of local feature descriptors degrades in the presence of large rotation variations. To address this issue, we present an efficient approach to learning rotation invariant descriptors. Specifically, we propose Rotated Kernel Fusion (RKF) which imposes rotations on the convolution kernel to improve the inherent nature of CNN. Since RKF can be processed by the subsequent re-parameteri...
