A 3D-guided data augmentation method generates world-consistent panoramic training data that improves a VLN agent's performance on unseen environments over prior augmentation baselines.
Vision-and-language navigation: Interpreting visually-grounded navigation instructions in real environments,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
World-Consistent Data Generation for Vision-and-Language Navigation
A 3D-guided data augmentation method generates world-consistent panoramic training data that improves a VLN agent's performance on unseen environments over prior augmentation baselines.