AI Paper Atlas

Research map / Image generation / Image restoration

AutoDIR: Automatic All-in-One Image Restoration with Latent Diffusion

Yitong Jiang, Zhaoyang Zhang, Tianfan Xue, Jinwei Gu

ECCV 2024 · Image generation › Image restoration · approach: Efficient restoration architectures · 99 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 semantic-agnostic regularization when fine-tuning CLIP for degradation detection (ablation)SA-CLIP BIQA · Degradation detection (7 degradations + clean)average accuracy: 83.31% -> 97.94%Improved
use CLIP with language prompts instead of a ViT-only classifier (ablation)BIQA stage · Degradation detection (7 degradations + clean)average accuracy: 77.65% -> 83.31%Improved
use original pre-trained CLIP without fine-tuning for degradation detection (ablation)BIQA stage · Degradation detection (7 degradations + clean)average accuracy: 61.96% vs 77.65% ViT-classifierHurt
add SA-BIQA guidance to the latent diffusion restoration (with SCM) (ablation)AutoDIR · DeraindropPSNR: 28.84 -> 30.10Improved
add SCM to the latent diffusion restoration (with SA-BIQA) (ablation)AutoDIR · DeraindropPSNR: 25.58 -> 30.10Improved
add SCM to the latent diffusion restoration (with SA-BIQA) (ablation)AutoDIR · DehazePSNR: 24.47 -> 29.34Improved
add SA-BIQA guidance (with SCM) (ablation)AutoDIR · DehazePSNR: 27.53 -> 29.34Improved
use small w (0.1) for the structural-correction module on super-resolution (ablation)SC-LDM · Super-resolutionperceptual quality (MUSIQ)Improved
use generative AutoDIR instead of discriminative PromptIR on super-resolutionAutoDIR · Super-resolutionPSNR: 29.62 -> 23.49Hurt
initialize desnowing fine-tuning from pre-trained all-in-one AIR weights (ablation)AIR backbone · Unseen de-snowing (CSD, 90 pairs)adaptation speedImproved

Later papers that compared with this method

6 later accepted papers report AutoDIR as a baseline in their results tables; 4 of them report a better number on most of the results they share with it.

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