UP-SLAM: Adaptively Structured Gaussian SLAM with Uncertainty Prediction in Dynamic Environments

TL;DR

UP-SLAM introduces a real-time RGB-D SLAM system that effectively handles dynamic environments by decoupling tracking and mapping, employing adaptive probabilistic structures, and estimating motion uncertainty without semantic labels, leading to improved accuracy and rendering quality.

Contribution

The paper presents UP-SLAM, a novel SLAM system that combines adaptive Gaussian primitives, a training-free uncertainty estimator, and a temporal encoder to enhance robustness and efficiency in dynamic scenes.

Findings

Outperforms state-of-the-art in localization accuracy by 59.8%.

Improves rendering quality with a 4.57 dB PSNR increase.

Maintains real-time performance while handling dynamic environments.

Abstract

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/