A unified, unsupervised CLIP-prompt-guided enhancement network with a residual U-Net and ASPP outperforms prior methods on backlit and low-light benchmarks.
In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
baseline 1
citation-polarity summary
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1roles
baseline 1polarities
baseline 1representative citing papers
citing papers explorer
-
UBLLIE: Unified Backlight and Low-Light Image Enhancement
A unified, unsupervised CLIP-prompt-guided enhancement network with a residual U-Net and ASPP outperforms prior methods on backlit and low-light benchmarks.