Transformers improve feature matching in images
Transformers improve feature matching in images
LoFTR: Detector-Free Local Feature Matching with Transformers
arXiv paper abstract https://arxiv.org/abs/2104.00680
arXiv PDF paper https://arxiv.org/pdf/2104.00680.pdf
... we propose to first establish pixel-wise dense matches at a coarse level and later refine the good matches at a fine level ... we use self and cross attention layers in Transformer to obtain feature descriptors that are conditioned on both images ... Transformer enables our method to produce dense matches in low-texture areas, where feature detectors usually struggle to produce repeatable interest points. The experiments on indoor and outdoor datasets show that LoFTR outperforms state-of-the-art methods by a large margin.
Paper Web site https://zju3dv.github.io/loftr
Please like and share this post if you enjoyed it using the buttons at the bottom!
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
Comentarios