AI Paper Atlas

Research map / Image generation / Super-resolution

Bridging Fidelity-Reality with Controllable One-Step Diffusion for Image Super-Resolution

Hao Chen, Junyang Chen, Jinshan Pan, Jiangxin Dong

CVPR 2026 · Image generation › Super-resolution · approach: Diffusion-based super-resolution · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add region-adaptive generative prior activation (RGPA) to base (ablation)CODSR base · DrealSRCLIPIQA+: 0.5038 -> 0.5109Improved
add RGPA to base (ablation)CODSR base · DrealSRLPIPS: 0.2906 -> 0.2914No clear effect
add LQFM alone to base (ablation)CODSR base · DrealSRMUSIQ: 65.89 -> 65.90No clear effect
add LQFM on top of RGPA (ablation)Base w/ RGPA · DrealSRFID: 133.02 -> 128.34Improved
add text-matching guidance (TMG) on top of RGPA and LQFM (ablation)Base w/ RGPA&LQFM · DrealSRCLIPIQA+: 0.5213 -> 0.5589Improved
add TMG on top of RGPA and LQFM (ablation)Base w/ RGPA&LQFM · DrealSRLPIPS: 0.2902 -> 0.2919Hurt
add adaptive noise to LQ image instead of latent (ablation)CODSR base · DrealSRCLIPIQA+: 0.5038 -> 0.5020No clear effect
use standard Gaussian noise in latent instead of adaptive noise (ablation)CODSR base · DrealSRPSNR (dB): 28.39 -> 28.04Hurt
replace SFT modulation with element-wise addition in LQFM (ablation)Base w/ RGPA&LQFM · DrealSRCLIPIQA+: 0.5213 -> 0.4956Hurt
modulate latent z_L instead of intermediate U-Net feature (ablation)Base w/ RGPA&LQFM · DrealSRCLIPIQA+: 0.5213 -> 0.5065Hurt
replace VSD loss with GAN loss in stage two (ablation)CODSR · DrealSRCLIPIQA+: 0.5589 -> 0.5009Hurt
increase forward timestep t_s (more adaptive noise) (ablation)CODSR · DrealSRPSNR vs MUSIQMixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy