AI Paper Atlas

Research map / Image generation / Image restoration

ReFusion: Learning Image Fusion from Reconstruction with Learnable Loss Via Meta-Learning

Haowen Bai, Zixiang Zhao, Jiangshe Zhang, Yichen Wu, Lilun Deng, Yukun Cui, Baisong Jiang, Shuang Xu

IJCV 2024 · Image generation › Image restoration · approach: Inverse imaging with learned priors · 56 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 learnable fusion loss weights w and v instead of fixed 1/2 (ablation)ReFusion · Infrared-visible fusion, MSRSSD: 37.49 -> 42.89Improved
add meta-learning training of the loss proposal module (ablation)ReFusion · Infrared-visible fusion, MSRSSD: 38.96 -> 42.89Improved
add separate fusion and reconstruction updates (ablation)ReFusion · Infrared-visible fusion, MSRSSD: 39.33 -> 42.89Improved
use max rather than sum in the reconstruction loss (ablation)ReFusion · Infrared-visible fusion, MSRSSD: 32.65 -> 42.89Improved
use learned feature fusion network instead of decision-based weighted sum (ablation)ReFusion · Infrared-visible fusion, MSRSSD: 38.42 -> 42.89Improved
use attention fusion module instead of concatenation (ablation)ReFusion · Infrared-visible fusion, MSRSSD: 39.26 -> 42.89Improved
add interactive feature extraction (ablation)ReFusion · Infrared-visible fusion, MSRSSD: 39.25 -> 42.89Improved
add gating feature refinement (ablation)ReFusion · Infrared-visible fusion, MSRSSD: 39.53 -> 42.89Improved
increase alpha1 from 1 to 10 in fusion loss (ablation)ReFusion · Infrared-visible fusion, MSRSSD: 42.89 -> 41.04Hurt
vary alpha2 between 0.1 and 10 (ablation)ReFusion · Infrared-visible fusion, MSRSSD: 42.72 to 42.89No clear effect
use ReFusion instead of CDDFuseCDDFuse · Infrared-visible fusion, MSRSSD: 43.38 vs 42.89Mixed
use ReFusion instead of DeFusionDeFusion · Medical image fusion, HarvardSSIM: 0.76 -> 0.75Hurt

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