Training a diffusion model on both enhancement and degradation paths, with a shared encoder and a reflection-aware correction module, yields state-of-the-art low-light enhancement on multiple benchmarks.
Title resolution pending
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
-
Degradation-Consistent Learning via Bidirectional Diffusion for Low-Light Image Enhancement
Training a diffusion model on both enhancement and degradation paths, with a shared encoder and a reflection-aware correction module, yields state-of-the-art low-light enhancement on multiple benchmarks.