RobustMat：面向挑战性环境下街道地标块匹配的神经扩散方法
RobustMat: Neural Diffusion for Street Landmark Patch Matching under Challenging Environments
AI总结：
本文提出 RobustMat，结合卷积神经 ODE 与图神经 PDE 扩散模块，利用邻域信息提升街景地标块在季节、天气和光照变化下的匹配鲁棒性，并在多个数据集上达到最先进性能。
摘要：
对于自动驾驶车辆（AV）而言，基于相机等传感器的视觉感知技术在信息获取与处理中发挥着关键作用。在面向自动驾驶车辆的各类计算机感知任务中，将车载相机拍摄的地标块与在不同时间捕获的、或保存在街景图像数据库中的其他地标块进行匹配，可能具有重要意义。为了在季节、天气和光照变化所导致的挑战性驾驶环境中完成匹配，我们利用每个地标块的空间邻域信息。我们提出了一种名为 RobustMat 的方法，其对扰动的鲁棒性源自神经微分方程。该方法使用卷积神经 ODE 扩散模块来学习地标块的特征表示；随后，图神经 PDE 扩散模块聚合街景中相邻地标块的信息；最后，特征相似性学习输出最终的匹配分数。我们的方法在多个街景数据集上进行了评估，结果表明其在环境扰动下取得了最先进的匹配性能。
英文摘要：
For autonomous vehicles (AVs), visual perception techniques based on sensors like cameras play crucial roles in information acquisition and processing. In various computer perception tasks for AVs, it may be helpful to match landmark patches taken by an onboard camera with other landmark patches captured at a different time or saved in a street scene image database. To perform matching under challenging driving environments caused by changing seasons, weather, and illumination, we utilize the spatial neighborhood information of each patch. We propose an approach, named RobustMat, which derives its robustness to perturbations from neural differential equations. A convolutional neural ODE diffusion module is used to learn the feature representation for the landmark patches. A graph neural PDE diffusion module then aggregates information from neighboring landmark patches in the street scene. Finally, feature similarity learning outputs the final matching score. Our approach is evaluated on several street scene datasets and demonstrated to achieve state-of-the-art matching results under environmental perturbations.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
