AI Paper Atlas

Research map / Image generation / Super-resolution

XPSR: Cross-modal Priors for Diffusion-based Image Super-Resolution

Qu Yunpeng, Kun Yuan, Kai Zhao, Qizhi Xie, Jinhua Hao, Ming Sun, Chao Zhou

ECCV 2024 · Image generation › Super-resolution · approach: Diffusion-based super-resolution · 29 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 high-level (and keep low-level) priors to semantic conditioning (ablation)XPSR · DRealSRFID: 195.37 -> 164.68Improved
add low-level priors (keep high-level) (ablation)XPSR · DRealSRMANIQA: 0.5505 -> 0.5713Improved
use parallel Semantic-Fusion Attention instead of serial cross-attention (ablation)XPSR · DRealSRSSIM: 0.6834 -> 0.7220Improved
add pixel and latent Degradation-Free Constraint (ablation)XPSR · DRealSRSSIM: 0.6979 -> 0.7220Improved
add negative prompts at inference (ablation)XPSR · DRealSRMUSIQ: 61.70 -> 67.84Improved
add negative prompts at inference (ablation)XPSR · DRealSRSSIM: 0.7355 -> 0.7220Hurt
use SD-v2.1 instead of SD-v1.5 as base model (ablation)XPSR · DRealSRMUSIQ: 67.84 -> 63.79Hurt
degrade LR input with JPEG compression or Gaussian blur before MLLM prompting (ablation)XPSR · DRealSRFID: 164.68 -> 175.77 (Gaussian blur)Hurt
use larger LLaVA-13b for prompts (ablation)XPSR · RealSRSSIM: 0.6870 -> 0.6920No clear effect
use XPSR instead of GAN-based and diffusion baselinesXPSR · DIV2K-ValPSNR: 24.42 (BSRGAN) vs 22.80 (XPSR)Hurt

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