Oneta uses one transformer-based network with switchable style tokens and a ten-dimensional eigentransformation basis to run six enhancement tasks across 30 datasets, though it falls far behind specialists on dehazing and extreme low-light.
When color constancy goes wrong: Correcting improperly white-balanced images
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
-
Oneta: Multi-Style Image Enhancement Using Eigentransformation Functions
Oneta uses one transformer-based network with switchable style tokens and a ten-dimensional eigentransformation basis to run six enhancement tasks across 30 datasets, though it falls far behind specialists on dehazing and extreme low-light.