W U Eastman Z Y

LIBA: Language Instructed Multi-granularity Bridge Assistant for 3D Visual Grounding

3D Vision Grounding (3D-VG) seeks to unravel referential language and identify targets in 3D physical world. Prevailing methods align with the 2D-VG's pipeline to pinpoint the referred object in a categorical multi-modal reasoning manner. However, the geometric complexities of 3D scenes and the nuan…