给视觉重定位的相机位姿预测加不确定度评估，提升可靠性。
Quantifying Epistemic Uncertainty in Absolute Pose Regression
- 用变分框架估计观测似然，量化位姿回归的信念不确定性。
- 在域外场景下仍能准确反映预测误差与不确定性的关系。
- 可处理重复结构带来的歧义，适合高精度定位应用。
视觉重定位旨在根据图像估计相机位姿。绝对位姿回归通过神经网络直接从图像特征回归位姿，具有内存和计算效率优势。然而，该方法在训练域外预测不准确且不可靠。本文提出一种新方法，在变分框架下估计观测的似然，以量化绝对位姿回归模型的主体性不确定性。该方法不仅能提供预测置信度，还统一处理观测歧义，在存在重复结构时概率性地定位相机。实验表明，本方法在捕捉不确定度与预测误差关系方面优于现有方法。
原文摘要 · Abstract (English)
Visual relocalization is the task of estimating the camera pose given an image it views. Absolute pose regression offers a solution to this task by training a neural network, directly regressing the camera pose from image features. While an attractive solution in terms of memory and compute efficiency, absolute pose regression's predictions are inaccurate and unreliable outside the training domain. In this work, we propose a novel method for quantifying the epistemic uncertainty of an absolute pose regression model by estimating the likelihood of observations within a variational framework. Beyond providing a measure of confidence in predictions, our approach offers a unified model that also handles observation ambiguities, probabilistically localizing the camera in the presence of repetitive structures. Our method outperforms existing approaches in capturing the relation between uncertainty and prediction error.
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。