A binary neural network fusing RAW frames and event streams achieves competitive low-light video enhancement at 20x lower compute than full-precision models.
Basic binary convolution unit for binarized image restoration network,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
EeveeDark: A Binary Neural Framework for Low-Light Video Enhancement via Event-Guided Sensor-Level Fusion
A binary neural network fusing RAW frames and event streams achieves competitive low-light video enhancement at 20x lower compute than full-precision models.