RIFT2-multimodal-matching-rotation
RIFT is designed for multimodal image feature matching. RIFT2 is the RIFT with new rotation invariant technique! If this code is helpful for you, please cite our work:
Li, Jiayuan, Qingwu Hu, and Mingyao Ai. "RIFT: Multi-modal image matching based on radiation-variation insensitive feature transform." IEEE Transactions on Image Processing 29 (2020): 3296-3310.
J. Li, W Xu, Q Hu, Y Zhang, “RIFT2: Speeding-up RIFT with A New Rotation-Invariance Technique,”