3D-LLaVA: Towards Generalist 3D LMMs with Omni Superpoint Transformer
Open paper
Benchmark
Model
Rank
Results
3d-dense-captioning-on-scan2cap
3D-LLaVA
#3
CIDEr: 78.8
ROUGE: 57.7
3d-question-answering-3d-qa-on-scanqa-val
3D-LLaVA
#3
CIDEr: 92.6
Rank counts only results with a code link.