XoFTR: Cross-modal Feature Matching Transformer

2024-06-16
Tuzcuoğlu, Önder
Köksal, Aybora
Sofu, Buğra
Kalkan, Sinan
Alatan, Abdullah Aydın
We introduce XoFTR a cross-modal cross-view method for local feature matching between thermal infrared (TIR) and visible images. Unlike visible images TIR images are less susceptible to adverse lighting and weather conditions but present difficulties in matching due to significant texture and intensity differences. Current hand-crafted and learning-based methods for visible-TIR matching fall short in handling viewpoint scale and texture diversities. To address this XoFTR incorporates masked image modeling pre-training and fine-tuning with pseudo-thermal image augmentation to handle the modality differences. Additionally we introduce a refined matching pipeline that adjusts for scale discrepancies and enhances match reliability through sub-pixel level refinement. To validate our approach we collect a comprehensive visible-thermal dataset and show that our method outperforms existing methods on many benchmarks. Code and dataset at https://github.com/OnderT/XoFTR.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
Citation Formats
Ö. Tuzcuoğlu, A. Köksal, B. Sofu, S. Kalkan, and A. A. Alatan, “XoFTR: Cross-modal Feature Matching Transformer,” presented at the Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Washington, Amerika Birleşik Devletleri, 2024, Accessed: 00, 2024. [Online]. Available: https://openaccess.thecvf.com/content/CVPR2024W/IMW/html/Tuzcuoglu_XoFTR_Cross-modal_Feature_Matching_Transformer_CVPRW_2024_paper.html.