DDN-SLAM: Real-time Dense Dynamic Neural Implicit SLAM with Joint Semantic Encoding

We propose DDN-SLAM, a real-time dense neural implicit These SLAM systems outperform traditional SLAM methods semantic SLAM system designed for dynamic scenes. in terms of texture details, memory consumption, noise While existing neural implicit SLAM systems perform well handling, and outlier processing. in static scenes, they often encounter challenges in realworld Although current neural implicit SLAM systems have environments with dynamic interferences, leading to achieved good reconstruction results in static scenes [8, ineffective tracking and mapping. DDN-SLAM utilizes the 24, 40, 78], many real-world environments are often affected priors provided by the deep semantic system, combined with by dynamic objects, especially in applications such conditional probability fields, for segmentation.By constructing as robotics or autonomous driving, which involve complex depth-guided static masks and employing joint physical environments and may also have low-texture areas multi-resolution hashing encoding, we ensure fast hole filling or significant changes in lighting and viewing angles. Current and high-quality mapping while mitigating the effects neural implicit SLAM systems are unable to achieve of dynamic information interference. To enhance tracking effective tracking and reliable reconstruction in such environments.