cs.CVNov 18, 2026

DetailScale-SR: Decoupling Restoration and Continuous Detail Control for Real-World Super-Resolution

Authors: Shengchuan Gao, Zhongjie Duan, Yingda Chen, Jingjing Chen

Organizations: Shanghai Jiao Tong University · ModelScope Team, Alibaba Group · Fudan University

Abstract

Real-world image super-resolution often seeks the most detailed plausible reconstruction, although more detail is not always desirable. The same degraded image may require restrained restoration, faithful reconstruction, or enhanced visual detail according to user intent. We present DetailScale-SR, a preference-conditioned framework that continuously controls reconstructed detail for a fixed low-resolution input without altering the scene being restored. Rather than relying on post-processing or repeatedly rewriting prompts, it learns a continuous family of reconstructions while separating content recovery from detail preference. This enables a smooth transition from conservative restoration to richly textured results under consistent input and semantic constraints. Its controllable range also extends beyond conventional restoration: DetailScale-SR can enhance high-frequency structures and generate perceptually richer textures than the paired high-resolution reference. Text restoration is another distinct strength. For text-rich scenes, especially Chinese posters and signs, it recovers more legible and character-faithful text than prior generative SR methods under matched textual guidance. DetailScale-SR therefore unifies continuous detail control, beyond-reference enhancement, and reliable recovery of semantically important content. Our model is available at https://modelscope.cn/models/DiffSynth-Studio/Qwen-Image-2.1-SR

Figures & tables

Explore similar work

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

    Mar 3, 2026Aro Kim, Myeongjin Jang, Chaewon Moon +3Image Super-ResolutionDiffusion Models for Image Restoration

  2. VICR: Visual In-Context Restoration for Real-World Image Super-Resolution

    May 30, 2026Qichang Zhang, Hailong Wang, Baiang Li +4Diffusion Models for Image RestorationImage Super-Resolution