A single auto-regressive model with hierarchical tokenization and a preference-based loss super-resolves images at multiple scale factors with competitive quality.
Toward real-world single image super-resolution: A new benchmark and a new model
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Multi-scale Image Super Resolution with a Single Auto-Regressive Model
A single auto-regressive model with hierarchical tokenization and a preference-based loss super-resolves images at multiple scale factors with competitive quality.