Contextual Modeling for 3D Dense Captioning on Point Clouds
Open paper
Benchmark
Model
Rank
Results
3d-dense-captioning-on-nr3d
Contextual
–
CIDEr: 35.26
BLEU-4: 20.42
METEOR: 22.77
ROUGE-L: 50.78
3d-dense-captioning-on-scanrefer-dataset
Contextual
–
CIDEr: 50.29
BLEU-4: 26.64
METEOR: 22.57
ROUGE-L: 44.71
Rank counts only results with a code link.