AI Paper Atlas

Research map / Image generation / Image restoration

Unsupervised Multi-Exposure Image Fusion Breaking Exposure Limits via Contrastive Learning

Han Xu, Liang Haochen, Jiayi Ma

AAAI 2023 · Image generation › Image restoration · approach: Dehazing and deraining · 18 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 MEF-CL instead of TransMEFMulti-exposure fusion on SICE · SICE test setMEF-SSIM: 0.907 ± 0.01 -> 0.911 ± 0.01Improved
Use MEF-CL instead of DeepfuseMulti-exposure fusion on SICE · SICE test setCC: 0.944 ± 0.02 -> 0.946 ± 0.03Improved
Use MEF-CL instead of DeepfuseMulti-exposure fusion on SICE · SICE test setPSNR: 58.687 ± 0.71 -> 58.604 ± 0.73Hurt
Use MEF-CL instead of IFCNNMulti-exposure fusion on SICE · SICE test setEI: 98.784 ± 0.75 -> 80.131 ± 0.68Hurt
Use MEF-CL instead of DeepfuseMulti-exposure fusion on SICE · SICE test setDeltaE: 13.790 ± 0.52 -> 13.572 ± 0.42Improved
Use MEF-CL instead of MEF-NetMulti-exposure fusion on SICE · SICE test setRuntime (second): 0.023 ± 0.01 -> 0.033 ± 0.01Hurt
Add LMSE (ablation)MEF-CL · SICE test setMEF-SSIM: 0.889 -> 0.911Improved
Add LSSIM (ablation)MEF-CL · SICE test setMEF-SSIM: 0.907 -> 0.911Improved
Add contrastive loss LInfoNCE (ablation)MEF-CL · SICE test setMEF-SSIM: 0.875 -> 0.911Improved
Add attribute block (ablation)MEF-CL · SICE test setMEF-SSIM: 0.876 -> 0.911Improved
Add content block (ablation)MEF-CL · SICE test setMEF-SSIM: 0.899 -> 0.911Improved
Add attribute block (ablation)MEF-CL · SICE test setEI: 74.465 -> 80.131Improved

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