Towards CLIP-Driven Language-Free 3D Visual Grounding via 2D-3D Relational Enhancement and Consistency

Yuqi Zhang, Han Luo, Yinjie LeiCVPR 2024 · DOI

BibTeX
@inproceedings{zhang2024towards,
  author = {Yuqi Zhang and Han Luo and Yinjie Lei},
  title = {{Towards CLIP-Driven Language-Free 3D Visual Grounding via 2D-3D Relational Enhancement and Consistency}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year = {2024},
  doi = {10.1109/cvpr52733.2024.01241},
}

Loading related content...

Figure