AI Paper Atlas

Research map / Architectures and efficiency / Mixture of experts

GM-MoE: Low-Light Enhancement with Gated-Mechanism Mixture-of-Experts

Minwen Liao, Haobo Dong, Xinyi Wang, Kurban Ubul, Yihua Shao, Ziyang Yan

ICCV 2025 · Architectures and efficiency › Mixture of experts · approach: Sparse MoE as regularization and attention · 17 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 shallow feature extraction block (SFEB) to the baseline (ablation)GM-MoE baseline · LOLv2-SyntheticPSNR: PSNR improved by 3.09 dB and SSIM improved by 0.0215Improved
add Expert1 (color restoration) to baseline+SFEB (ablation)GM-MoE · LOLv2-RealPSNR: PSNR increased by 1.08 dB (20.27 -> 21.35)Improved
add Expert2 (detail enhancement) after Expert1 (ablation)GM-MoE · LOLv2-Real and LOLv2-SyntheticPSNR: PSNR increased by 0.76 dB (LOL-v2-real) and 0.79 dB (LOL-v2-syn), SSIM increased by 0.0575 and 0.0891Improved
add the gated weight generation network to the three-expert model without Net3 (ablation)GM-MoE · LOLv2-RealPSNR: 22.11 -> 23.23Improved
add Expert3 to the model with gating and Experts 1-2 (ablation)GM-MoE · LOLv2-RealPSNR: 23.23 -> 23.65Improved
add Expert2 to the model with gating and Experts 1 and 3 (ablation)GM-MoE · LOLv2-RealPSNR: 23.31 -> 23.65Improved
add Expert1 to the model with gating and Experts 2 and 3 (ablation)GM-MoE · LOLv2-RealPSNR: 23.35 -> 23.65Improved
use dynamic gating instead of fixed expert weights (ablation)GM-MoE · LOLv2-RealPSNR: 21.70 -> 23.65Improved
mix experts in parallel with gating instead of serializing them (ablation)GM-MoE · LOLv2-RealPSNR: PSNR 21.34 -> 23.65, SSIM 0.83 -> 0.80Mixed
use gated weighted sum instead of channel concat plus 1x1 fusion of experts (ablation)GM-MoE · LOLv2-RealPSNR: 17.84 -> 23.65Improved
GM-MoE versus the next best method on LSRW datasetsGM-MoE vs Restormer · LSRW-Huawei and LSRW-NikonPSNR: PSNR improvements of 0.94 dB and 1.42 dBImproved

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