提出轻量级不确定性估计框架，提升匹配精度与可靠性
Semi-Dense Matching Uncertainty Is Not Just Local Confidence
- 用9个可学习参数的混合拉普拉斯模型捕捉局部噪声和粗匹配失败
- 在多种预训练匹配器上显著提升几何估计精度，误差分布更完整
- 适合需要可靠匹配结果的视觉系统，如三维重建与定位
可靠的半密集匹配对现代几何视觉系统至关重要。现有方法多采用从粗到精的范式，在性能与计算成本间取得平衡，但常无法准确量化不确定性，忽略灾难性粗匹配失败，导致误差分布被截断，严重误导几何估计。本文提出一种轻量级、后置式整体不确定性估计框架，引入仅含9个可学习参数的双组件校准拉普拉斯混合模型，显式建模局部精化噪声与粗匹配失败的长尾分布。我们提出粗匹配成功后验重校正（CoRe）方法，利用粗匹配成功的后验概率作为软对应权重进行几何重校正。大量实验表明，该方法在多种仅预训练匹配器和鲁棒估计算法上均显著提升下游几何精度，且计算开销极低。代码已开源。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。