A Transformer architecture with a learned dynamic integral-image illumination estimator and illumination-guided attention achieves small but consistent PSNR and SSIM gains over prior low-light enhancement methods on six public datasets.
Learning to see moving objects in the dark,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
SAIGFormer: A Spatially-Adaptive Illumination-Guided Network for Low-Light Image Enhancement
A Transformer architecture with a learned dynamic integral-image illumination estimator and illumination-guided attention achieves small but consistent PSNR and SSIM gains over prior low-light enhancement methods on six public datasets.