CVJul 18, 2022

Adaptive Assignment for Geometry Aware Local Feature Matching

arXiv:2207.08427v357 citationsh-index: 73Has Code
Originality Incremental advance
AI Analysis

This addresses a bottleneck in computer vision for applications like 3D reconstruction, but it is incremental as it builds on existing matching methods.

The paper tackles the problem of geometry inconsistency in detector-free feature matching under large-scale and viewpoint variations by introducing AdaMatcher, which uses adaptive assignment and scale estimation, achieving state-of-the-art results on downstream tasks.

The detector-free feature matching approaches are currently attracting great attention thanks to their excellent performance. However, these methods still struggle at large-scale and viewpoint variations, due to the geometric inconsistency resulting from the application of the mutual nearest neighbour criterion (\ie, one-to-one assignment) in patch-level matching.Accordingly, we introduce AdaMatcher, which first accomplishes the feature correlation and co-visible area estimation through an elaborate feature interaction module, then performs adaptive assignment on patch-level matching while estimating the scales between images, and finally refines the co-visible matches through scale alignment and sub-pixel regression module.Extensive experiments show that AdaMatcher outperforms solid baselines and achieves state-of-the-art results on many downstream tasks. Additionally, the adaptive assignment and sub-pixel refinement module can be used as a refinement network for other matching methods, such as SuperGlue, to boost their performance further. The code will be publicly available at https://github.com/AbyssGaze/AdaMatcher.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes