AI Paper Atlas

Research map / Image generation / Image restoration

A Unified Conditional Framework for Diffusion-based Image Restoration

Yi Zhang, Xiaoyu Shi, Dasong Li, Xiaogang Wang, Jian Wang, Hongsheng Li

NeurIPS 2023 · Image generation › Image restoration · approach: Diffusion-based universal restoration · 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 the unified conditional diffusion framework instead of the strongest listed baselineImage restoration · SIDLPIPS: 0.338 -> 0.222Improved
Use the unified conditional diffusion framework instead of the strongest listed baselineImage restoration · GoProLPIPS: 0.084 -> 0.080Improved
Use the unified conditional diffusion framework instead of the strongest listed baselineImage restoration · ImageNet JPEG restoration, Quality Factor 10LPIPS: 0.205 -> 0.139Improved
Add LayerNorm to the diffusion block (ablation)Conditional diffusion framework · SIDLPIPS: 0.227 -> 0.222Improved
Use LayerNorm rather than GroupNorm (ablation)Conditional diffusion framework · SIDLPIPS: 0.240 -> 0.222Improved
Use Swish rather than ReLU (ablation)Conditional diffusion framework · SIDLPIPS: 0.235 -> 0.222Improved
Add initial-predictor spatial guidance (ablation)Conditional diffusion framework · SIDLPIPS: 0.240 -> 0.222Improved
Use initial-predictor output rather than internal features as spatial guidance (ablation)Conditional diffusion framework · SIDLPIPS: 0.247 -> 0.222Improved
Use initial-predictor output rather than the degraded image as spatial guidance (ablation)Conditional diffusion framework · SIDLPIPS: 0.253 -> 0.222Improved
Use adaptive kernel integration rather than direct addition (ablation)Conditional diffusion framework · SIDLPIPS: 0.236 -> 0.222Improved
Use adaptive kernel integration rather than concatenation (ablation)Conditional diffusion framework · SIDLPIPS: 0.241 -> 0.222Improved
Use adaptive kernel integration rather than AdaIN (ablation)Conditional diffusion framework · SIDLPIPS: 0.240 -> 0.222Improved

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