OpenOcc: Open Vocabulary 3D Scene Reconstruction via Occupancy Representation

arXiv:2403.11796v1 Announce Type: new
Abstract: 3D reconstruction has been widely used in autonomous navigation fields of mobile robotics. However, the former research can only provide the basic geometry structure without the capability of open-world scene understanding, limiting advanced tasks like human interaction and visual navigation. Moreover, traditional 3D scene understanding approaches rely on expensive labeled 3D datasets to train a model for a single task with supervision. Thus, geometric reconstruction with zero-shot scene understanding i.e. Open vocabulary 3D Understanding and …

3d reconstruction abstract advanced arxiv autonomous basic capability cs.cv cs.ro fields geometry however human mobile navigation open-world representation research robotics tasks type understanding via visual visual navigation world