Gassidy让3D高斯点云在动态环境中更准更稳地重建场景。
Gassidy: Gaussian Splatting SLAM in Dynamic Environments
- 用光照几何损失函数分析渲染误差流，区分动/静物体。
- 动态物体干扰下相机定位精度提升97.9%，地图质量提高6%。
- 适合复杂动态场景下的实时3D重建，如机器人导航。
3D高斯点云（3DGS）可灵活调整场景表示，在静态环境下支持密集视觉同时定位与地图构建（SLAM）的连续优化。然而，面对运动不规则的动态物体干扰时，3DGS会降低相机定位精度和地图重建质量。为此，我们提出一种名为Gassidy的RGB-D密集SLAM方法，通过设计光度-几何损失函数计算高斯分布的渲染损失流，对环境各部分进行逐帧分析。通过迭代检测动态物体与静态组件间损失值变化特征，实现干扰分离，确保干净环境用于精确重建。在公开数据集上的实验表明，相比前沿SLAM方法，Gassidy将相机跟踪精度最高提升97.9%，地图质量提升最高达6%。
原文摘要 · Abstract (English)
3D Gaussian Splatting (3DGS) allows flexible adjustments to scene representation, enabling continuous optimization of scene quality during dense visual simultaneous localization and mapping (SLAM) in static environments. However, 3DGS faces challenges in handling environmental disturbances from dynamic objects with irregular movement, leading to degradation in both camera tracking accuracy and map reconstruction quality. To address this challenge, we develop an RGB-D dense SLAM which is called Gaussian Splatting SLAM in Dynamic Environments (Gassidy). This approach calculates Gaussians to generate rendering loss flows for each environmental component based on a designed photometric-geometric loss function. To distinguish and filter environmental disturbances, we iteratively analyze rendering loss flows to detect features characterized by changes in loss values between dynamic objects and static components. This process ensures a clean environment for accurate scene reconstruction. Compared to state-of-the-art SLAM methods, experimental results on open datasets show that Gassidy improves camera tracking precision by up to 97.9% and enhances map quality by up to 6%.
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。