AI Paper Atlas

Research map / Image generation / Image restoration

MoE-DiffIR: Task-customized Diffusion Priors for Universal Compressed Image Restoration

Yulin Ren, Xin Li, Bingchen Li, Xingrui Wang, Mengxi China Guo, Shijie Zhao, Li Zhang, Zhibo Chen

ECCV 2024 · Image generation › Image restoration · approach: Efficient restoration architectures · 11 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
use MoE-Prompt instead of soft-weighted multiple prompts (ablation)MoE-DiffIR · LIVE1 seen tasksLPIPS: 0.1212 -> 0.1179Improved
use MoE-Prompt instead of a single prompt (ablation)MoE-DiffIR · LIVE1 seen tasksLPIPS: 0.1272 -> 0.1179Improved
add prompts at all (MoE-Prompt vs no prompt) (ablation)MoE-DiffIR · ICB unseen Cross TypesFID: 210.84 -> 176.87Improved
add Visual2Text adapter to MoE-Prompt (ablation)MoE-DiffIR · LIVE1 (21 tasks)LPIPS: 0.1179 -> 0.1145Improved
add degradation prior (DP) to router (ablation)MoE-DiffIR · LIVE1 (21 tasks)PSNR: 29.02 -> 29.07Improved
fine-tune VAE decoder with LQ information (decoder compensator) (ablation)MoE-DiffIR · LIVE1 (avg 21 tasks)PSNR: 22.70 -> 29.03Improved
train VAE from scratch instead of fine-tuning decoder (ablation)MoE-DiffIR · LIVE1 (avg 21 tasks)PSNR: 29.03 -> 25.12Hurt
select K=1 prompt instead of K=3 (ablation)MoE-Prompt router · LIVE1LPIPS / PSNRMixed
use too many prompts (N above 7) (ablation)MoE-Prompt · LIVE1PSNR/LPIPSNo clear effect
MoE-DiffIR versus StableSR on distortionMoE-DiffIR · seven codecs averagePSNR: +0.41dBImproved

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