Semi-Dense Matching Uncertainty Is Not Just Local Confidence

2026-08-09

AI Summary

This work addresses the challenge of accurately quantifying uncertainty in existing semi-dense matching methods, which often overlook catastrophic failures during the coarse matching stage, leading to biased geometric estimates. To remedy this, the authors propose a lightweight post-processing framework that explicitly incorporates coarse matching failures into uncertainty modeling. Specifically, they introduce a two-component calibrated Laplacian mixture model with only nine learnable parameters to capture the long-tailed distribution arising from both local refinement noise and coarse matching outliers. Additionally, a CoRe (Coarse-and-Refined) geometric refitting module is designed to leverage Bayesian posterior probabilities for generating soft correspondence weights, enabling reweighted optimization. The method consistently improves downstream geometric accuracy across diverse pretrained matchers and robust estimators while incurring minimal computational overhead.

Abstract

Reliable semi-dense matching is essential for modern geometric vision systems. Designed under a coarse-to-fine paradigm, it achieves an optimal balance between performance and computational cost. However, existing methods often struggle to provide well-quantified uncertainties, where catastrophic coarse-assignment failures are ignored, leading to truncated error distributions and severely misjudged geometric estimations. In this paper, we propose a lightweight, post-hoc overall uncertainty estimation framework that introduces a two-component calibrated Laplace mixture model with only 9 learnable parameters. The objective is to explicitly capture both the sharp local refinement noise and the broader tail of coarse-assignment failures. We introduce the Coarse-success posterior Refit (CoRe) method, a geometric refitting module that utilizes the posterior probability of coarse-assignment success as soft correspondence weights. Extensive experiments show that our method consistently improves downstream geometric accuracy across various pretrained-only matchers and robust estimators with minimal computational overhead. Our code is available at https://github.com/khoavpt/Probabilistic-matching.

Problem

• semi-dense matching
• uncertainty quantification
• coarse-to-fine matching
• geometric vision
• matching failure

Innovation

• semi-dense matching
• uncertainty estimation
• Laplace mixture model
• coarse-to-fine paradigm
• geometric vision