TESO：通过随机优化在线跟踪本质矩阵
TESO: Online Tracking of Essential Matrix by Stochastic Optimization
提出一种在本质矩阵流形上做在线随机优化的方法，用核相关鲁棒损失函数直接优化稀疏对应点，无需训练即可在线跟踪双目外参漂移，对资源受限的视觉感知系统有直接复用价值。
原文依据 an adaptive online stochastic optimization on the essential manifold
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论保持双目相机标定参数的长期精度对自主系统的感知至关重要。本文提出通过随机优化在线跟踪本质矩阵（TESO）。TESO 的核心机制是：1）基于核相关、作用于暂定对应点的鲁棒损失函数；2）在本质流形上的自适应在线随机优化。TESO 的 CPU 和内存需求低，依赖少量超参数，且无需数据驱动训练，因而可用于资源受限的在线感知系统。我们评估了 TESO 对几何精度、校正质量和双目深度一致性的影响。在大规模 MAN TruckScenes 数据集上，TESO 以 0.12 度的精度跟踪 Y 轴（对双目精度至关重要）的旋转标定漂移，而 X 轴和 Z 轴的精度高五倍。将跟踪应用于模拟漂移的序列时，其相对于参考的精度与应用于无漂移序列时相似，表明跟踪器是无偏的。在 KITTI 数据集上，TESO 揭示了双目对之间外参的系统性不一致，证实了此前已发表的研究结果。我们验证了内参失校准影响了这些误差，校正和深度指标相互矛盾的行为证明了这一点。在校正参考标定后，TESO 将 Y 轴附近的旋转精度提高了 20 倍，达到 0.025 度，深度精度提高了 50 倍。尽管设计轻量，仅直接优化所提出的 TESO 损失函数即可达到与基于神经网络的单帧方法相当的精度。
英文原文摘要 1720 字符
Maintaining long-term accuracy of stereo camera calibration parameters is important for autonomous systems' perception. This work proposes Online Tracking of Essential Matrix by Stochastic Optimization (TESO). The core mechanisms of TESO are: 1) a robust loss function based on kernel correlation over tentative correspondences, 2) an adaptive online stochastic optimization on the essential manifold. TESO has low CPU and memory requirements, relies on a few hyperparameters, and eliminates the need for data-driven training, enabling the usage in resource-constrained online perception systems. We evaluated the influence of TESO on geometric precision, rectification quality, and stereo depth consistency. On the large-scale MAN TruckScenes dataset, TESO tracks rotational calibration drift with 0.12 deg precision in the Y-axis-critical for stereo accuracy-while the X- and Z-axes are five times more precise. Tracking applied to sequences with simulated drift shows similar precision with respect to the reference as tracking applied to no-drift sequences, indicating the tracker is unbiased. On the KITTI dataset, TESO revealed systematic inconsistencies in extrinsic parameters across stereo pairs, confirming previous published findings. We verified that intrinsic decalibration affected these errors, as evidenced by the conflicting behavior of the rectification and depth metrics. After correcting the reference calibration, TESO improved its rotation precision around the Y-axis 20 times to 0.025 deg and its depth accuracy 50 times. Despite its lightweight design, direct optimization of the proposed TESO loss function alone achieves accuracy comparable to that of neural network-based single-frame methods.