Unifying 2D and 3D Vision-Language Understanding

Open paper
Benchmark Model Rank Results
3d-visual-grounding-on-scanrefer-valUniVLG#1Acc@0.25: 63.5Acc@0.5: 56.4
3d-question-answering-3d-qa-on-scanqa-valUniVLG#4CIDEr: 78.5

Rank counts only results with a code link.