End-To-End RGB-D SLAM with Multi-MLPs Dense Neural Implicit Representations

An accurate and generalizable dense 3D recon- struction system has attracted much attention. However, exist- ing 3D dense reconstruction systems are constrained by pre- training, and there is a need for enhanced reconstruction of texture and shape details. We propose an end-to-end 3D reconstruction system which achieves fine scene reconstruc- tion without prior information by utilizing a neural implicit encoding. Our proposed system successfully achieves the goal through improved multi-MLP decoders (MLM) and an effective keyframe selection strategy. Experiments conducted on the commonly used Replica and TUM RGB-D datasets demonstrate that our approach can compete with widely adopted NeRF- based SLAM methods in terms of 3D reconstruction accuracy. Moreover, our approach shows a 40.8%(except Completion Ratio) improvement in accuracy compared to NICE-SLAM [14] and does not use prior information.