“…Neural Implicit-based SLAM. Neural implicit representations [65] have shown great performance in many different tasks, including object-level reconstruction reconstruction [28,4,40,41,26,36,69], scene completion [42,24,17], novel view synthesis [29,44,72,31,64], etc. In terms of SLAM-related applications, some works [70,23,61,6,1,8] try to jointly optimize a neural radiance field and camera poses, but they are only applicable to small objects or small camera movements.…”