DeepMatcher: A deep transformer-based network for robust and accurate local feature matching

Tao Xie, Kun Dai, Ke Wang, Ruifeng Li, Lijun Zhao

Abstract: Highlights•We propose DeepMatcher, a deep Transformer-based network for local feature matching.•We propose SlimFormer to enable DeepMatcher to be extended into dozen layers.•We propose FTM to ensure a smooth transition from CNN to SlimFormer.•We propose FMM to optimize coarse matches, deriving robust and accurate matches.