A 3D-language feature field pretrained on about 5,000 indoor scenes with nearly a million text descriptions improves vision-language navigation, zero-shot object navigation, and situated question answering.
Bevbert: Multimodal map pre-training for language-guided navigation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
g3D-LF: Generalizable 3D-Language Feature Fields for Embodied Tasks
A 3D-language feature field pretrained on about 5,000 indoor scenes with nearly a million text descriptions improves vision-language navigation, zero-shot object navigation, and situated question answering.