LL-ICM jointly trains a neural image codec and a vision-language-guided diffusion restorer, claiming large bit-rate savings for low-level machine vision tasks.
Learning transferable visual models from natural language supervision,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
other 1
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1roles
other 1polarities
unclear 1representative citing papers
citing papers explorer
-
LL-ICM: Image Compression for Low-level Machine Vision via Large Vision-Language Model
LL-ICM jointly trains a neural image codec and a vision-language-guided diffusion restorer, claiming large bit-rate savings for low-level machine vision tasks.