Depth Anything V2 delivers finer, more robust monocular depth predictions by replacing real labeled images with synthetic data, scaling the teacher model, and using large-scale pseudo-labeled real images for student training.
Objects365: A large-scale, high-quality dataset for object detection
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
dataset 1
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
UNVERDICTED 1roles
dataset 1polarities
use dataset 1representative citing papers
citing papers explorer
-
Depth Anything V2
Depth Anything V2 delivers finer, more robust monocular depth predictions by replacing real labeled images with synthetic data, scaling the teacher model, and using large-scale pseudo-labeled real images for student training.