XoFTR: Cross-modal Feature Matching Transformer
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914755182067712 |
|---|---|
| author | Tuzcuoğlu, Önder Köksal, Aybora Sofu, Buğra Kalkan, Sinan Alatan, A. Aydın |
| author_facet | Tuzcuoğlu, Önder Köksal, Aybora Sofu, Buğra Kalkan, Sinan Alatan, A. Aydın |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_09692 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | XoFTR: Cross-modal Feature Matching Transformer Tuzcuoğlu, Önder Köksal, Aybora Sofu, Buğra Kalkan, Sinan Alatan, A. Aydın Computer Vision and Pattern Recognition 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. |
| title | XoFTR: Cross-modal Feature Matching Transformer |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2404.09692 |