Lexicon3D: Probing Visual Foundation Models for Complex 3D Scene Understanding
Open paper
Benchmark
Model
Rank
Results
3d-question-answering-3d-qa-on-scanqa-val
Lexicon3D (DINOv2)
#5
CIDEr: 73.2
question-answering-on-sqa3d
Lexicon3D
#9
AnswerExactMatch (Question Answering): 50.7
Rank counts only results with a code link.