用高阶微分提升大运动下的光流精度，尤其适合纹理缺失场景。
Robust Optical Flow Computation: A Higher-Order Differential Approach
- 基于二阶泰勒展开改进微分估计，增强对复杂运动的建模能力。
- 在KITTI和Middlebury数据集上平均端点误差显著降低。
- 特别适用于大位移、弱纹理区域的光流计算，适合自动驾驶视觉系统。
在计算机视觉中，光流是理解动态视觉场景的核心技术。然而，在大非线性运动条件下准确估计光流仍是未解难题，图像流约束易受大位移和快速空间变换影响，数值微分固有的不精确性会进一步加剧问题。为此，本文提出一种创新的光流计算算法，利用二阶泰勒级数逼近在微分估计框架中的更高精度。通过这一数学基础，算法能更充分捕捉函数在复杂真实场景下的行为，有效估计无纹理区域的运动。在知名光流基准测试如KITTI (2015) 和 Middlebury 上表现优异，平均端点误差（AEE）明显下降，验证了其在处理复杂运动模式方面的有效性。
原文摘要 · Abstract (English)
In the domain of computer vision, optical flow stands as a cornerstone for unraveling dynamic visual scenes. However, the challenge of accurately estimating optical flow under conditions of large nonlinear motion patterns remains an open question. The image flow constraint is vulnerable to substantial displacements, and rapid spatial transformations. Inaccurate approximations inherent in numerical differentiation techniques can further amplify such intricacies. In response, this research proposes an innovative algorithm for optical flow computation, utilizing the higher precision of second-order Taylor series approximation within the differential estimation framework. By embracing this mathematical underpinning, the research seeks to extract more information about the behavior of the function under complex real-world scenarios and estimate the motion of areas with a lack of texture. An impressive showcase of the algorithm's capabilities emerges through its performance on renowned optical flow benchmarks such as KITTI (2015) and Middlebury. The average endpoint error (AEE), which computes the Euclidian distance between the calculated flow field and the ground truth flow field, stands notably diminished, validating the effectiveness of the algorithm in handling complex motion patterns.
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。