Most existing dynamic SLAM methods integrating neural networks require high computational support and pre-defined categories of dynamic objects. This paper proposes an online visual SLAM system without pre-defined dynamic labels for dynamic environments, which is built on ORB-SLAM3. We combine semantic information, depth information and optical flow to distinguish foreground and background and recognize dynamic regions. The foreground points in dynamic areas are regarded as moving points. We also restore static points on moving objects by the average re-projection error between multiple frames to adapt to non-rigid motion and low-dynamic environments. In pose optimization, we define an optimization weight for every point to decrease the negative influence of potential dynamic points. The experiments on TUM RGB-D and Bonn datasets show that OVD-SLAM achieves more accurate and robust localization than other state-of-art dynamic SLAM methods. To further verify our system’s online performance and robustness, we also test it in real dynamic scenes and apply it to an AR application using a handheld RGB-D camera.

SLAM systems based on NeRF have demonstrated superior performance in rendering quality and scene reconstruction for static environments compared to traditional dense SLAM. However, they encounter tracking drift and mapping errors in real-world scenarios with dynamic interferences. To address these issues, we propose DDN-SLAM, a real-time dense dynamic neural implicit SLAM system integrating semantic features. To address dynamic tracking interferences, we propose a feature point segmentation method that combines semantic features with a mixed Gaussian distribution model. To avoid incorrect background removal, we propose a mapping strategy based on sparse point cloud sampling and background restoration. We propose a dynamic semantic loss to eliminate dynamic occlusions. Experimental results demonstrate that DDN-SLAM is capable of robustly tracking and producing high-quality reconstructions in dynamic environments, while appropriately preserving potential dynamic objects. Compared to existing neural implicit SLAM systems, the tracking results on dynamic datasets indicate an average 90% improvement in Average Trajectory Error (ATE) accuracy.

Monocular SLAM has received a lot of attention due to its simple RGB inputs and the lifting of complex sensor constraints. However, existing monocular SLAM systems lack accurate depth estimation, which limits the accuracy of tracking and mapping performance. To address this limitation, we propose MoD-SLAM, the first monocular NeRF-based dense mapping method that allows 3D reconstruction in real-time in unbounded scenes. Specifically, we introduce a depth estimation module in the front-end to extract accurate priori depth values to supervise mapping and tracking processes. This strategy is essential to improve the SLAM performance. Moreover, a Gaussian-based unbounded scene representation approach is designed to solve the challenge of mapping scenes without boundaries. By introducing a robust depth loss term into the tracking process, our SLAM system achieves more precise pose estimation in large-scale scenes. Our experiments on two standard datasets show that MoD-SLAM achieves competitive performance, improving the accuracy of the 3D reconstruction and localization by up to 30% and 15% respectively compared with existing monocular SLAM systems.

Gaussian Splatting SLAMs have made significant advancements in improving the efficiency and fidelity of real-time reconstructions. However, these systems often encounter incomplete reconstructions in complex indoor environments, characterized by substantial holes due to unobserved geometry caused by obstacles or limited view angles. To address this challenge, we present Manhattan Gaussian SLAM, an RGB-D system that leverages the Manhattan World hypothesis to enhance geometric accuracy and completeness. By seamlessly integrating fused line segments derived from structured scenes, our method ensures robust tracking in textureless indoor areas. Moreover, The extracted lines and planar surface assumption allow strategic interpolation of new Gaussians in regions of missing geometry, enabling efficient scene completion. Extensive experiments conducted on both synthetic and real-world scenes demonstrate that these advancements enable our method to achieve state-of-the-art performance, marking a substantial improvement in the capabilities of Gaussian SLAM systems.