DRKF: Distilled Rotated Kernel Fusion for Efficient Rotation Invariant Descriptors in Local Feature Matching
This work addresses a key challenge in computer vision for applications like drone navigation by improving descriptor robustness to rotation, though it is incremental as it builds on existing CNN-based methods.
The paper tackles the degradation of local feature descriptors under large rotation variations by proposing DRKF, which combines Rotated Kernel Fusion and Multi-oriented Feature Aggregation to learn rotation-invariant descriptors, achieving state-of-the-art performance on datasets like HPatches and a new DiverseBEV dataset.
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-parameterization, no extra computational costs will be introduced in the inference stage. Moreover, we present Multi-oriented Feature Aggregation (MOFA) which aggregates features extracted from multiple rotated versions of the input image and can provide auxiliary knowledge for the training of RKF by leveraging the distillation strategy. We refer to the distilled RKF model as DRKF. Besides the evaluation on a rotation-augmented version of the public dataset HPatches, we also contribute a new dataset named DiverseBEV which is collected during the drone's flight and consists of bird's eye view images with large viewpoint changes and camera rotations. Extensive experiments show that our method can outperform other state-of-the-art techniques when exposed to large rotation variations.