S2DNet: Learning Accurate Correspondences for Sparse-to-Dense Feature Matching
This addresses the need for precise feature matching in computer vision applications, representing an incremental improvement over existing methods.
The paper tackled the problem of establishing robust and accurate correspondences in computer vision by introducing S2DNet, a feature matching pipeline that achieves state-of-the-art results on the HPatches benchmark and several long-term visual localization datasets.
Establishing robust and accurate correspondences is a fundamental backbone to many computer vision algorithms. While recent learning-based feature matching methods have shown promising results in providing robust correspondences under challenging conditions, they are often limited in terms of precision. In this paper, we introduce S2DNet, a novel feature matching pipeline, designed and trained to efficiently establish both robust and accurate correspondences. By leveraging a sparse-to-dense matching paradigm, we cast the correspondence learning problem as a supervised classification task to learn to output highly peaked correspondence maps. We show that S2DNet achieves state-of-the-art results on the HPatches benchmark, as well as on several long-term visual localization datasets.