DarkDiff fine-tunes Stable Diffusion with region-based cross-attention, a residual VAE, and a pixel-space loss to turn noisy linear-RGB low-light images into clean sRGB photos, achieving top LPIPS on SID, ELD, and LRD.
Learning to see 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
-
DarkDiff: Advancing Low-Light Raw Enhancement by Retasking Diffusion Models for Camera ISP
DarkDiff fine-tunes Stable Diffusion with region-based cross-attention, a residual VAE, and a pixel-space loss to turn noisy linear-RGB low-light images into clean sRGB photos, achieving top LPIPS on SID, ELD, and LRD.