Method Drift›Mixture-of-experts routing
Superseded baseline#311 of 1,370 most-superseded
GLARE
GLARE: Low Light Image Enhancement via Generative Latent Feature based Codebook RetrievalMixture-of-experts routing · first seen Jul 17, 2024
superseded — cited as a baseline and beaten by newer methods
0 papers critique it · 1 beat it on benchmarks
Beaten on benchmarks
Head-to-head results where a newer method reports beating GLARE. Values are copied from the source paper's tables — verify against the cited paper.
- ISALux: Illumination and Segmentation Aware Transformer Employing Mixture of Experts for Low Light Image Enhancement
ISALux beats GLARE · Average PSNR [LOL-v1, LOL-v2-Real, LOL-v2-Synthetic, SDSD-in, SDSD-out datasets]
30.08 vs 29.42
- ISALux: Illumination and Segmentation Aware Transformer Employing Mixture of Experts for Low Light Image Enhancement
ISALux beats GLARE · Average NIQE [No-Reference Datasets (MEF, LIME, DICM, NPE)]
3.34 vs 3.99
Newer alternatives
Recent methods in the same sub-problem, not yet superseded in the knowledge base.