2 papers
cs.CV2025
Advancing 3D Scene Understanding with MV-ScanQA Multi-View Reasoning Evaluation and TripAlign Pre-training Dataset
Wentao Mo, Qingchao Chen, Yuxin Peng +2
The advancement of 3D vision-language (3D VL) learning is hindered by several limitations in existing 3D VL datasets: they rarely necessitate reasoning beyond a close range of obje…
cs.CV2024
3D Vision and Language Pretraining with Large-Scale Synthetic Data
Dejie Yang, Zhu Xu, Wentao Mo +3
3D Vision-Language Pre-training (3D-VLP) aims to provide a pre-train model which can bridge 3D scenes with natural language, which is an important technique for embodied intelligen…