发表机构
University of Bath（巴斯大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文通过合成室内场景的对照实验，研究纹理稀缺时动态点滤波对ORB-SLAM2前端的影响，发现滤波仅在高动态场景中有益，GEOM误移除静态特征更多且在立体模式下优势消失。
AI 中文摘要
动态点滤波器通常被添加到基于特征的视觉SLAM系统中，而近期若干系统指出，在低纹理区域移除动态特征可能会导致静态特征数量过少。迄今为止，这些系统仅在纹理丰富的基准序列上进行了评估。本文开展了一项对照研究，以分离上述交互作用：我们渲染了合成室内序列，其中表面纹理（分为四个等级，通过FAST角点密度和图像梯度熵量化）与场景动态性（分为三个等级）沿相同相机轨迹进行因子变化，同时提供了立体、RGB-D、真实位姿及动态掩码。在该网格上，我们对比了未使用滤波的ORB-SLAM2、使用光流与对极残差滤波（FLOW）的ORB-SLAM2，以及使用多视图深度一致性滤波（GEOM）的ORB-SLAM2，在五次运行中记录了轨迹误差、跟踪完整性及存活静态特征数量。由于掩码提供了每个关键点的真实值，我们还测量了各滤波器的动态点精确率、召回率及静态特征误移除率，以便直接验证机制性解释。本文未提出新的滤波器。在24个序列的720次运行中，滤波主要在动态性最高的单元中发挥作用；其收益并未随纹理单调下降，但在最低纹理等级下，滤波会降低跟踪完整性，且ORB-SLAM2从未在静态L3场景中完成初始化。与我们的假设相反，GEOM比FLOW丢弃了更多静态关键点（RGB-D下的中位数误移除率FRR为6.8%，FLOW为1.5%；立体模式下为19.6%，FLOW为1.5%）；其在RGB-D模式下的优势与动态点召回率相关，在立体模式下消失。数据和代码可在该https URL获取。
英文摘要
Dynamic-point filters are routinely added to feature-based visual SLAM, and several recent systems argue that removing dynamic features can leave too few static features in low-texture regions. So far, these systems have been evaluated only on texture-rich benchmark sequences. We present a controlled study that isolates this interaction. We render synthetic indoor sequences in which surface texture (four levels, quantified by FAST-corner density and image-gradient entropy) and scene dynamics (three levels) are varied factorially along identical camera trajectories, with stereo, RGB-D, ground-truth poses and dynamic masks. On this grid we compare ORB-SLAM2 without filtering, with an optical-flow and epipolar-residual filter (FLOW), and with a multi-view depth-consistency filter (GEOM), and report trajectory error, tracking completeness and surviving static features over five runs. Because the masks give per-keypoint ground truth, we also measure each filter's dynamic-point precision and recall and its static-feature false-removal rate, so that mechanistic explanations can be tested directly. We do not propose a new filter. On 720 runs over 24 sequences, filtering helped mainly in the most dynamic cells; the benefit did not decline monotonically with texture, but at the lowest level filtering reduced tracking completeness, and ORB-SLAM2 never initialised in static L3 scenes. Contrary to our hypothesis, GEOM discarded more static keypoints than FLOW (median FRR 6.8% vs. 1.5% for RGB-D, 19.6% vs. 1.5% for stereo); its RGB-D advantage tracked dynamic-point recall and vanished in stereo mode. Data and code are available at https://github.com/felixxxue/texture-dynamics-slam.
Comments8 pages, 4 figures, submitted to IROS 2026. Open-source code and dataset available
