UP-SLAM在动态环境中实现高精度实时定位与渲染，无需依赖语义标签。
UP-SLAM: Adaptively Structured Gaussian SLAM with Uncertainty Prediction in Dynamic Environments
- 采用并行框架分离追踪与建图，用概率八叉树自适应管理高斯点。
- 训练无关的不确定性估计器提升动态物体处理能力，定位精度提升59.8%。
- 适合需要实时高保真地图的机器人、AR/VR应用，尤其在复杂动态场景中表现优异。
近年来，基于3D高斯溅射（3DGS）的视觉同时定位与建图（SLAM）技术在追踪和高保真建图方面取得显著进展。然而，其顺序优化框架及对动态物体的敏感性限制了在真实场景中的实时性能与鲁棒性。本文提出UP-SLAM，一种面向动态环境的实时RGB-D SLAM系统，通过并行化框架解耦追踪与建图。采用概率八叉树自适应管理高斯原语，实现高效初始化与修剪，无需手工设定阈值。为在追踪中鲁棒过滤动态区域，提出无需训练的不确定性估计算法，融合多模态残差估计像素级运动不确定性，实现开集动态物体处理，无需依赖语义标签。此外，设计时间编码器提升渲染质量；通过浅层MLP高效转换低维特征，构建DINO特征以丰富高斯场，增强不确定性预测鲁棒性。大量实验表明，UP-SLAM在多个挑战性数据集上优于现有最先进方法，定位精度提升59.8%，渲染质量提高4.57 dB PSNR，同时保持实时性能，并生成可复用、无伪影的静态地图。
原文摘要 · Abstract (English)
Recent 3D Gaussian Splatting (3DGS) techniques for Visual Simultaneous Localization and Mapping (SLAM) have significantly progressed in tracking and high-fidelity mapping. However, their sequential optimization framework and sensitivity to dynamic objects limit real-time performance and robustness in real-world scenarios. We present UP-SLAM, a real-time RGB-D SLAM system for dynamic environments that decouples tracking and mapping through a parallelized framework. A probabilistic octree is employed to manage Gaussian primitives adaptively, enabling efficient initialization and pruning without hand-crafted thresholds. To robustly filter dynamic regions during tracking, we propose a training-free uncertainty estimator that fuses multi-modal residuals to estimate per-pixel motion uncertainty, achieving open-set dynamic object handling without reliance on semantic labels. Furthermore, a temporal encoder is designed to enhance rendering quality. Concurrently, low-dimensional features are efficiently transformed via a shallow multilayer perceptron to construct DINO features, which are then employed to enrich the Gaussian field and improve the robustness of uncertainty prediction. Extensive experiments on multiple challenging datasets suggest that UP-SLAM outperforms state-of-the-art methods in both localization accuracy (by 59.8%) and rendering quality (by 4.57 dB PSNR), while maintaining real-time performance and producing reusable, artifact-free static maps in dynamic environments.The project: https://aczheng-cai.github.io/up_slam.github.io/
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。