Method Towards CVPR 2021 SimLocMatch Challenge

This report describes Megvii-3D team’s approach towards SimLocMatch Challenge @ CVPR 2021 Image Matching Workshop. It includes the submissions: • aaa-1000k 50 no ms111 • aaa-1000k 80 no ms111 • aaa-1000k no ms • aaa-1000k no ms2 • sss-sd 100k 8 • sss-sd 100k 1 • sss-sd 100k 6 The methodology we took is similar to our solution towards CVPR 2021 Image Matching Challenge, hence we only report the additional strategies and tricks besides it.

[1]  Jiri Matas,et al.  Two-view geometry estimation unaffected by a dominant plane , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[2]  Tomasz Malisiewicz,et al.  SuperGlue: Learning Feature Matching With Graph Neural Networks , 2019, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Tomasz Malisiewicz,et al.  SuperPoint: Self-Supervised Interest Point Detection and Description , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).