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.
A style-based generator architecture for generative adversarial networks
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Conditional score-based diffusion models synthesize phase maps from magnitude-only MR images to generate k-space datasets that train superior deep learning models for accelerated MRI reconstruction compared to smooth-phase or GAN-based alternatives.
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.
-
Phase-map synthesis from magnitude-only MR images using conditional score-based diffusion models with application in training of accelerated MRI reconstruction models
Conditional score-based diffusion models synthesize phase maps from magnitude-only MR images to generate k-space datasets that train superior deep learning models for accelerated MRI reconstruction compared to smooth-phase or GAN-based alternatives.