用概率迭代优化解决多模态图像配准难题，提升配准精度与可靠性。
RBE-Flow: Recurrent Bayesian Estimation on Feature Manifolds for Cross-Modal Registration
- 将配准建模为特征流形上的循环贝叶斯估计，实现自校正
- 在多个基准上达到领先性能，子像素级误差降低显著
- 适合需要高精度配准的遥感、医学影像等场景
多模态图像配准对多传感器感知至关重要，但因严重的非线性辐射差异和几何畸变而极具挑战。现有确定性匹配方法缺乏不确定性感知，难以应对高度非凸的优化问题，常在模糊区域累积误差。本文提出RBE-Flow，将密集多模态光流估计重构为在学习特征流形上的闭环循环贝叶斯估计问题。不同于传统前馈回归，RBE-Flow通过深度耦合特征度量非线性优化与概率状态更新，构建鲁棒自校正机制。具体地，递归流形优化（RMO）模块迭代生成光流观测及其不确定性，再通过不确定性自适应概率更新（UAPU）结合确定性sigma点投影，最优融合至先验状态。关键在于，得到的校准后验协方差被反馈用于自适应调节后续优化步的阻尼，使系统根据预测置信度动态调控收敛过程。为保障稳定概率训练，引入几何感知的修正负对数似然（NLL）损失，有效防止方差坍缩。在OSdataset、WHU-OPT-SAR和RoadScene等多个挑战性基准上实验表明，RBE-Flow持续取得最先进性能，尤其在严格子像素标准下优势明显。
原文摘要 · Abstract (English)
Cross-modal image registration is essential for multi-sensor perception but remains fundamentally challenging due to severe non-linear radiometric discrepancies and geometric distortions. Existing deterministic matching methods lack uncertainty awareness, struggling to navigate the resulting highly non-convex optimization landscape and frequently accumulating errors in ambiguous regions. In this paper, we propose RBE-Flow, a novel framework that reformulates dense cross-modal flow estimation as a closed-loop recurrent Bayesian estimation problem on learned feature manifolds. Diverging from standard feed-forward regression, RBE-Flow establishes a robust self-correcting mechanism by deeply coupling feature-metric non-linear optimization with probabilistic state updates. Specifically, a Recurrent Manifold Optimization (RMO) block iteratively generates flow observations and their associated uncertainties, which are then optimally assimilated into the prior state via an Uncertainty-Adaptive Probabilistic Update (UAPU) using deterministic sigma-point projection. Crucially, the resulting calibrated posterior covariance is fed back to adaptively regularize the damping of subsequent optimization steps, allowing the system to modulate its convergence based on predictive confidence. To ensure stable probabilistic training, we introduce a hybrid supervision scheme featuring a geometry-aware rectified NLL loss that structurally prevents variance collapse. Extensive experiments on challenging OSdataset, WHU-OPT-SAR, and RoadScene benchmarks demonstrate that RBE-Flow consistently achieves state-of-the-art performance, outperforming existing methods by a significant margin, particularly under strict sub-pixel criteria. Project page: https://github.com/NEU-Liuxuecong/RBE-Flow
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。