Bird-SR outperforms prior super-resolution methods on real images by guiding diffusion trajectories with bidirectional rewards, early structure optimization on synthetic pairs, and later perceptual rewards with dynamic balancing.
Maniqa: Multi-dimension attention network for no-reference image quality assessment
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2verdicts
UNVERDICTED 2representative citing papers
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.
citing papers explorer
-
Bird-SR: Bidirectional Reward-Guided Diffusion for Real-World Image Super-Resolution
Bird-SR outperforms prior super-resolution methods on real images by guiding diffusion trajectories with bidirectional rewards, early structure optimization on synthetic pairs, and later perceptual rewards with dynamic balancing.
-
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.