Efficient and Accurate Co-Visible Region Localization with Matching Key-Points Crop (MKPC): A Two-Stage Pipeline for Enhancing Image Matching Performance

TL;DR

This paper introduces MKPC, a two-stage image matching pipeline that efficiently crops co-visible regions to improve accuracy, demonstrating superior performance on challenging outdoor benchmarks.

Contribution

The paper presents MKPC, a novel cropping algorithm and a flexible two-stage pipeline that enhances existing image matching models for outdoor pose estimation.

Findings

Outperforms state-of-the-art on Image Matching Challenge 2022

Improves outdoor pose estimation accuracy

Compatible with various image matching models

Abstract

Image matching is a classic and fundamental task in computer vision. In this paper, under the hypothesis that the areas outside the co-visible regions carry little information, we propose a matching key-points crop (MKPC) algorithm. The MKPC locates, proposes and crops the critical regions, which are the co-visible areas with great efficiency and accuracy. Furthermore, building upon MKPC, we propose a general two-stage pipeline for image matching, which is compatible to any image matching models or combinations. We experimented with plugging SuperPoint + SuperGlue into the two-stage pipeline, whose results show that our method enhances the performance for outdoor pose estimations. What's more, in a fair comparative condition, our method outperforms the SOTA on Image Matching Challenge 2022 Benchmark, which represents the hardest outdoor benchmark of image matching currently.