← Search

Yuqi Shen

1 accepted papers

2026

Beyond Ground-Truth: Leveraging Image Quality Priors for Real-World Image Restoration

CVPR 2026

Real-world image restoration aims to restore high-quality (HQ) images from degraded low-quality (LQ) inputs captured under uncontrolled conditions. Existing methods typically depend on ground-truth (GT) supervision, assuming that GT provides perfect reference quality. However, GT can still contain i

Cited by 4SourcecodeScholar