AI Paper Atlas

Research map / Image generation / Image restoration

DeepFuse: A Deep Unsupervised Approach for Exposure Fusion With Extreme Exposure Image Pairs

K. Ram Prabhakar, V Sai Srikar, R. Venkatesh Babu

ICCV 2017 · Image generation › Image restoration · approach: Dehazing and deraining · 801 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
fuse features by addition instead of product (ablation)DeepFuse · 23 test imagesaverage MEF SSIM: 0.8210 -> 0.9782Improved
fuse features by addition instead of concatenation (ablation)DeepFuse · 23 test imagesaverage MEF SSIM: 0.9430 -> 0.9782Improved
fuse features by addition instead of max (ablation)DeepFuse · 23 test imagesaverage MEF SSIM: 0.9638 -> 0.9782Improved
fuse features by addition instead of mean (ablation)DeepFuse · 23 test imagesaverage MEF SSIM: 0.9750 -> 0.9782No clear effect
train with MEF SSIM unsupervised loss instead of imitating Mertens/GFF outputs (ablation)DeepFuse · MEF SSIM test sequencesMEF SSIM: DF-Baseline 0.9477 -> DF-UnSupervised 0.9813 on AgiaGaliniImproved
use SSIM loss instead of l2 for supervised baseline (ablation)DF-Baseline · test sequencesvisual qualityImproved
tie weights of the two pre-fusion channelsDeepFuse · test sequencesparameters/convergenceImproved
use DeepFuse with 3 input images instead of MertensDeepFuse · 3-image sequencesaverage MEF SSIM: 0.979 -> 0.987Improved
use DeepFuse with 4 input images instead of MertensDeepFuse · 4-image sequencesaverage MEF SSIM: 0.978 -> 0.972Hurt
run DeepFuse instead of MertensDeepFuse · 1920*1200 image pairrunning time (s): 2.76 -> 0.82Improved

Later papers that compared with this method

3 later accepted papers report DeepFuse as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.

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