SOURCE-LINKED INTELLIGENCE

Uncertainty-Guided Latent Diffusion Models for Faithful Super Resolution

arXiv · AI, language, vision and robotics · article · Aug 26, 2026 · UTC

The perception-distortion trade-off poses a fundamental challenge in single-image super-resolution (SR). Although diffusion-based SR methods excel at generating perceptually realistic images, achieving high fidelity remains a key limitation. Recent advances in diffusion-based SR have shown promise in improving fidelity, but these methods often compromise perceptual quality due to their high reliance on a high-fidelity image. To address this, we introduce UGDiff, a novel diffusion guidance paradigm designed to further improve the perception-distortion balance. In particular, we first estimate t

Read original source ↗ Open in workspace

recordType

paper

region

Global