Aug, 2023

三维点云视觉锚定的统一框架

TL;DR3D point cloud visual grounding encompasses 3D referring expression comprehension (3DREC) and segmentation (3DRES), and this paper proposes a unified framework called 3D Referring Transformer (3DRefTR) that integrates 3DREC and 3DRES, achieving superior performance on the ScanRefer dataset.