Scene-LLM: Extending Language Model for 3D Visual Understanding and Reasoning
Open paper
Benchmark
Model
Rank
Results
3d-question-answering-3d-qa-on-scanqa-test-w
Scene-LLM
–
Exact Match: 27.2
BLEU-4: 12.0
ROUGE: 40.0
METEOR: 16.6
CIDEr: 80
3d-question-answering-3d-qa-on-sqa3d
Scene-LLM
–
Exact Match: 54.2
Rank counts only results with a code link.