collaborators

1 paper

cs.CV2024

PD-APE: A Parallel Decoding Framework with Adaptive Position Encoding for 3D Visual Grounding

Chenshu Hou, Liang Peng, Xiaopei Wu +2

3D visual grounding aims to identify objects in 3D point cloud scenes that match specific natural language descriptions. This requires the model to not only focus on the target obj…