BIR-Adapter adds a parameter-efficient attention adapter and guided sampling to pretrained diffusion models, achieving competitive blind image restoration performance with up to 36x fewer trained parameters and enabling extension to new degradation types.
export NEGATIVE_PROMPT =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
BIR-Adapter: A parameter-efficient diffusion adapter for blind image restoration
BIR-Adapter adds a parameter-efficient attention adapter and guided sampling to pretrained diffusion models, achieving competitive blind image restoration performance with up to 36x fewer trained parameters and enabling extension to new degradation types.