AI Paper Atlas

Research map / Image generation / Super-resolution

Disentangled Textual Priors for Diffusion-based Image Super-Resolution

Lei Jiang, Xin Liu, Xinze Tong, Zhiliang Li, Jie Liu, Jie Tang, Gangshan Wu

CVPR 2026 · Image generation › Super-resolution · approach: Diffusion-based super-resolution · 0 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 local (object-level) text priors (ablation)DTPSR · DRealSRMUSIQ: 67.48 -> 68.86Improved
add global text prior on top of local priors (ablation)DTPSR · DRealSRMUSIQ: 68.86 -> 69.24Improved
add global prior only (no local) (ablation)DTPSR · DRealSRMUSIQ: 67.48 -> 67.80Improved
add high-frequency prior on top of low-frequency prior (ablation)DTPSR · DRealSRCLIP-IQA: 0.7544 -> 0.7640Improved
add low-frequency prior on top of high-frequency prior (ablation)DTPSR · DRealSRMANIQA: 0.5495 -> 0.6011Improved
disentangle LF and HF into separate cross-attention branches instead of a mixed sentence (ablation)DTPSR · DRealSRCLIP-IQA: 0.7527 -> 0.7640Improved
add multi-branch negative prompts instead of none (ablation)DTPSR · DRealSRMUSIQ: 66.73 -> 69.24Improved
use single generic negative prompt instead of none (ablation)DTPSR · DRealSRMANIQA: 0.5995 -> 0.5776Hurt
multi-branch negative prompts instead of single generic negative prompt (ablation)DTPSR · DRealSRCLIP-IQA: 0.7499 -> 0.7640Improved
corrupt textual descriptions by replacing words with None (ablation)DTPSR · Table 7 (labelled DRealSR)MUSIQ: 71.84 -> 71.64No clear effect
disentangled textual priors vs best baselines on perceptual metricsDTPSR · DIV2K-ValPSNR: 24.62 -> 22.03Hurt
use DTPSR vs FaithDiffDTPSR · DRealSRMUSIQ: 66.30 -> 69.24Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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