Embodiedocc: Embodied 3d occupancy prediction for vision-based online scene understanding
3D occupancy prediction provides a comprehensive description of the surrounding scenes
and has become an essential task for 3D perception. Most existing methods focus on offline …
and has become an essential task for 3D perception. Most existing methods focus on offline …
ViGiL3D: A Linguistically Diverse Dataset for 3D Visual Grounding
3D visual grounding (3DVG) involves localizing entities in a 3D scene referred to by natural
language text. Such models are useful for embodied AI and scene retrieval applications …
language text. Such models are useful for embodied AI and scene retrieval applications …