-
MonoSelfRecon
MonoSelfRecon: Purely Self-Supervised Explicit Generalizable 3D Reconstruction of Indoor Scenes from Monocular RGB Views -
Scannet: Richly-annotated 3D reconstructions of indoor scenes
Scannet: Richly-annotated 3D reconstructions of indoor scenes. -
ScanNet Dataset
The ScanNet dataset is a large-scale indoor dataset composed of monocular sequences with ground truth poses and depth images.