“…There have been many 3D scene representations, such as multiview images [60,77], textured meshes [38,85], point clouds [1,61], and voxels [42,75]. Recently, some methods [11,41,44,51,76,96,103] propose implicit neural representations to represent scenes, which uses MLP networks to predict scene properties for any point in 3D space, such as occupancy [44,67], signed distance [41,51], and semantics [23,103]. This enables them to describe continuous and high-resolution 3D scenes.…”