【ACCV2022】MatchFormer: Interleaving Attention in Transformers for Feature Matching

MatchFormer: Interleaving Attention in Transformers for Feature Matching

MatchFormer是在LoFTR基础上进行改进

链接：MatchFormer: Interleaving Attention in Transformers for Feature Matching | SpringerLink
代码：jamycheung/MatchFormer: Repository of MatchFormer (github.com)

Abstract

Local feature matching is a computationally intensive task at the subpixel level. While detector-based methods coupled with feature descriptors struggle in low-texture scenes, CNN-based methods with a sequential extract-to-match pipeline, fail to make use of the matching capacity of the encoder and tend to overburden the decoder for matching. In contrast,