AI Paper Atlas

Research map / Image generation / Super-resolution

One-Step Flow for Image Super-Resolution with Tunable Fidelity-Realism Trade-offs

Yuanzhi Zhu, Ruiqing Wang, Shilin Lu, Hanshu Yan, Junnan Li, Kai Zhang

ICLR 2026 · Image generation › Super-resolution · approach: Diffusion-based super-resolution

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 Gaussian noise perturbation sigma_p=0.1 to LR initial state (ablation)conditional flow · FFHQ 256 4x SRFID: 110.29 -> 30.54Improved
increase sigma_p from 0.1 to 1 (ablation)conditional flow · FFHQ 256 4x SRNFEs / FID: NFE 20 -> 44; FID 30.54 -> 30.75Hurt
condition on LR image (ablation)conditional flow · FFHQ 256 4x SRFID: 42.47 -> 30.54Improved
use l1 loss instead of l2 (ablation)conditional flow · FFHQ 256 4x SRFID: 31.86 -> 30.54Improved
use proposed distillation loss instead of BOOT (ablation)one-step student · FFHQ 256 4x SRLPIPS: 0.483 -> 0.065Improved
use proposed loss instead of PINN loss (ablation)one-step student · FFHQ 256 4x SRLPIPS: 0.250 -> 0.065Improved
add alignment and boundary losses plus midpoint solver (ablation)one-step student · FFHQ 256 4x SRLPIPS: 0.065 -> 0.056Improved
reduce dt from 0.05 to 0.001 (ablation)one-step student · FFHQ 256 4x SRLPIPS: 0.065 -> 0.160Hurt
lower t from 1 to 0 at inferenceone-step student · FFHQ 256 4x SRPSNR vs LPIPS: PSNR 28.98 -> 31.25; LPIPS 0.055 -> 0.150Mixed
distill with one step instead of 20 NFE teacherOFTSR · FFHQ 256 4x SRLPIPS: 0.053 -> 0.055No clear effect
distill ResShift teacher with OFTSR loss instead of SinSRone-step student · ImageNet 256 4x SRFID: 94.90 -> 60.64Improved

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