3D-VisTA: Pre-trained Transformer for 3D Vision and Text Alignment

Benchmark Model Rank Results
3d-question-answering-3d-qa-on-scanqa-test-w3D-VisTA#7Exact Match: 22.4BLEU-4: 10.4ROUGE: 35.7METEOR: 13.9CIDEr: 69.6
3d-question-answering-3d-qa-on-sqa3d3D-VisTA#5Exact Match: 48.5