KFS$^4$LAM: Adaptive KeyFrame Selection with Structure-Aware Mapping for Endoscopic Gaussian Splatting SLAM

📄 arXiv: 2610.22505v1 📥 PDF

作者: Xinwei Ju, Zhehua Mao, Tianyi Song, Danail Stoyanov, Sophia Bano, Francisco Vasconcelos

分类: cs.CV

发布日期: 2026-10-15

备注: 8 pages, 5 figures, 3 tables

🔗 代码/项目: PROJECT_PAGE


💡 一句话要点

提出KFS$^4$LAM以解决内窥镜SLAM中的关键帧选择问题

🎯 匹配领域: 支柱三:空间感知与语义 (Perception & Semantics)

关键词: 内窥镜SLAM 关键帧选择 高斯喷溅 结构监督 运动引导

📋 核心要点

  1. 现有SLAM方法在内窥镜应用中面临关键帧选择不可靠的问题,导致冗余或遗漏重要视角。
  2. KFS$^4$LAM通过运动引导的自适应关键帧选择与结构监督映射,优化了关键帧的选择过程。
  3. 在C3VD-v2数据集上,KFS$^4$LAM相较于基线方法显著降低了旋转相对姿态误差20.3%,深度均方根误差降低38.4%。

📝 摘要(中文)

高斯喷溅同时定位与地图构建(SLAM)增强了传统SLAM,通过密集的可渲染3D场景表示,实现高质量重建和新视角合成。然而,其定位、重建和渲染性能高度依赖于保留的观测数据。现有系统通常依赖固定的时间间隔或简单的姿态和重叠标准进行关键帧选择。在结肠镜检查中,由于相机运动不均匀、解剖结构重复、镜面反射和视觉伪影,这些标准可能不可靠,导致冗余关键帧或遗漏重要视角。本文提出KFS$^4$LAM,结合运动引导的自适应关键帧选择与结构监督映射,强调结构信息区域,同时限制时间变形以适应局部组织动态。实验表明,KFS$^4$LAM在C3VD和C3VD-v2数据集上表现优异,尤其在C3VD-v2上显著提升性能。

🔬 方法详解

问题定义:本文旨在解决内窥镜SLAM中关键帧选择的可靠性问题。现有方法依赖固定时间间隔或简单标准,导致冗余或遗漏重要视角,影响重建质量。

核心思路:KFS$^4$LAM结合运动引导的自适应关键帧选择与结构监督映射,利用运动信息和结构特征来优化关键帧选择,确保保留重要视角并抑制冗余。

技术框架:该方法包括三个主要模块:运动引导的关键帧选择、密度感知的映射与解剖轮廓监督、以及限制时间变形的处理。整体流程通过这些模块协同工作,提升SLAM性能。

关键创新:KFS$^4$LAM的主要创新在于将运动引导与结构监督结合,形成了一种新的关键帧选择机制,显著提高了在复杂场景下的SLAM性能。

关键设计:在设计中,采用了运动信息来引导关键帧选择,使用解剖结构的轮廓作为监督信号,并通过限制时间变形来适应局部组织动态,避免几何漂移。

🖼️ 关键图片

img_0
img_1
img_2

📊 实验亮点

KFS$^4$LAM在C3VD-v2数据集上表现出色,旋转相对姿态误差降低20.3%,深度均方根误差降低38.4%,并且PSNR提升0.78 dB,显示出其在复杂场景下的显著优势。

🎯 应用场景

该研究在内窥镜检查、医学成像和机器人导航等领域具有广泛的应用潜力。通过提高SLAM的精度和可靠性,KFS$^4$LAM可以帮助医生更好地进行诊断和治疗,同时为机器人在复杂环境中的自主导航提供支持。

📄 摘要(原文)

Gaussian-splatting Simultaneous Localization and Mapping (SLAM) augments conventional SLAM with a dense, renderable 3D scene representation, enabling high-quality reconstruction and novel-view synthesis. However, its localization, reconstruction, and rendering performance depends strongly on which observations are retained for mapping. Existing systems commonly rely on fixed temporal intervals or simple pose- and overlap-based criteria for keyframe selection. In colonoscopy, non-uniform camera motion, repetitive anatomy, specularities, and visual artifacts can make these criteria unreliable, leading to either redundant keyframes or missed informative viewpoints. We present KFS$^4$LAM (KeyFrame Selection with Structure-aware mapping for endoscopic Gaussian Splatting SLAM), which couples motion-guided adaptive keyframe selection with structurally supervised mapping and restricted temporal deformation. Accumulated motion guides adaptive keyframe selection, with complementary cues suppressing redundant or unreliable candidates. Density-aware mapping with anatomical contour supervision (colon folds) emphasizes structurally informative regions, while restricted temporal deformation accommodates local tissue dynamics without unconstrained geometric drift. We evaluate KFS$^4$LAM against Gaussian-SLAM baselines on C3VD and C3VD-v2, together with cross-backbone and component ablations. KFS$^4$LAM achieves strong overall performance across trajectory, rendering, and depth metrics, with pronounced gains on more challenging C3VD-v2 dataset. In the matched comparison with SplaTAM on C3VD-v2, it reduces rotational relative pose error by 20.3% and depth RMSE by 38.4%, while improving PSNR by 0.78 dB. Cross-backbone experiments further show that the framework is not tied to a single underlying SLAM architecture. Code and visualization results are available at https://xinweiju.github.io/KFSLAM/.