SURE: Semi-dense Uncertainty-REfined Feature Matching

TL;DR

SURE introduces a semi-dense feature matching framework that jointly predicts correspondences and their confidence by modeling uncertainties, improving reliability in challenging robotic vision scenarios.

Contribution

It presents a novel evidential head and spatial fusion module for uncertainty-aware semi-dense matching, outperforming existing methods in accuracy and efficiency.

Findings

Outperforms state-of-the-art semi-dense matching models

Consistently improves accuracy on standard benchmarks

Enhances reliability in challenging scenarios

Abstract

Establishing reliable image correspondences is essential for many robotic vision problems. However, existing methods often struggle in challenging scenarios with large viewpoint changes or textureless regions, where incorrect cor- respondences may still receive high similarity scores. This is mainly because conventional models rely solely on fea- ture similarity, lacking an explicit mechanism to estimate the reliability of predicted matches, leading to overconfident errors. To address this issue, we propose SURE, a Semi- dense Uncertainty-REfined matching framework that jointly predicts correspondences and their confidence by modeling both aleatoric and epistemic uncertainties. Our approach in- troduces a novel evidential head for trustworthy coordinate regression, along with a lightweight spatial fusion module that enhances local feature precision with minimal overhead. We evaluated our method on multiple standard benchmarks, where it consistently outperforms existing state-of-the-art semi-dense matching models in both accuracy and efficiency. our code will be available on https://github.com/LSC-ALAN/SURE.