← Search

Aro Kim

1 accepted papers

2026

FiDeSR: High-Fidelity and Detail-Preserving One-Step Diffusion Super-Resolution

CVPR 2026

Diffusion-based approaches have recently driven remarkable progress in real-world image super-resolution (SR). However, existing methods still struggle to simultaneously preserve fine details and ensure high-fidelity reconstruction, often resulting in suboptimal visual quality. In this paper, we pro

Cited by 0SourcecodeScholar