AI Paper Atlas

Research map / Image generation / Image restoration

ReCoNet: Recurrent Correction Network for Fast and Efficient Multi-Modality Image Fusion

Zhanbo Huang, Jinyuan Liu, Xin Fan, Risheng Liu, Wei Zhong, Zhongxuan Luo

ECCV 2022 · Image generation › Image restoration · approach: Image harmonization and color transformation · 217 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 the micro registration module to the fusion networkReCoNet · Computational efficiency (GPU)Model size (M params): 0.007 -> 0.209Hurt
add the micro registration module to the fusion networkReCoNet · Computational efficiency (GPU)Runtime (s): 0.024 -> 0.052Hurt
add the micro registration module to the fusion networkReCoNet · Computational efficiency (GPU)FLOPs (G): 1.162 -> 12.54Hurt
increase recurrent attention iterations (ablation)ReCoNet · Infrared-visible fusionvisual qualityImproved
add the deformable alignment (micro registration) module (ablation)ReCoNet · Misaligned TNO/RoadScenevisual artifactsImproved
use ReCoNet against DenseFuse, PMGI, DIDFuse, U2Fusion under added transformsReCoNet · Misaligned TNO/RoadSceneCCImproved

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