Introduces LSTR and ESTR low-light text datasets and shows joint LLIE-OCR training outperforms standalone models.
Properties and performance of a center/surround retinex
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
SADM adds a signal attenuation coefficient to the diffusion forward process so that reverse denoising simultaneously recovers brightness and suppresses noise without extra stages or correction modules.
citing papers explorer
-
Reading in the Dark: Low-light Scene Text Recognition
Introduces LSTR and ESTR low-light text datasets and shows joint LLIE-OCR training outperforms standalone models.
-
Single-Stage Signal Attenuation Diffusion Model for Low-Light Image Enhancement and Denoising
SADM adds a signal attenuation coefficient to the diffusion forward process so that reverse denoising simultaneously recovers brightness and suppresses noise without extra stages or correction modules.