DeepSPG combines Retinex decomposition with image-level semantic features from HRNet and text-level CLIP alignment to improve low-light image enhancement, reporting state-of-the-art PSNR/SSIM on LOL-v1, LOL-v2-synthetic, and SID.
Band representation-based semi-supervised low-light image enhancement: Bridging the gap between signal fidelity and perceptual quality
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
-
DeepSPG: Exploring Deep Semantic Prior Guidance for Low-light Image Enhancement with Multimodal Learning
DeepSPG combines Retinex decomposition with image-level semantic features from HRNet and text-level CLIP alignment to improve low-light image enhancement, reporting state-of-the-art PSNR/SSIM on LOL-v1, LOL-v2-synthetic, and SID.