SOURCE-LINKED INTELLIGENCE

GraftSR: Grafting Authentic Textures for Real-World Image Super-Resolution via Identical-Instance Guidance

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

Diffusion-based real-world image super-resolution (SR) achieves impressive perceptual quality but inherently suffers from severe texture hallucination. To overcome this limitation, we propose GraftSR, a texture-reference-guided generative SR framework that leverages reference images of the identical instance to anchor the restoration of authentic textures. However, severe spatial misalignment between low-quality inputs and their references poses significant challenges, often leading to ambiguous transfer targets and background feature leakage. To address these issues, GraftSR employs a novel d

Read original source ↗ Open in workspace

recordType

paper

region

Global