Scaling masked autoencoding video transformers from 20M to 22B parameters steadily improved camera pose, tracking, and depth estimation, while language-supervised and image-only models lagged on these tasks.
Objects that sound
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
-
Scaling 4D Representations
Scaling masked autoencoding video transformers from 20M to 22B parameters steadily improved camera pose, tracking, and depth estimation, while language-supervised and image-only models lagged on these tasks.