In VAR-based super-resolution, K2N predicts the first three coarse scales in parallel from the low-resolution input and generates only the remaining fine scales autoregressively, reducing hallucination while staying competitive on standard metrics.
Title resolution pending
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
-
Detail Continuation over a Trustworthy Coarse Scale for Autoregressive Super-Resolution
In VAR-based super-resolution, K2N predicts the first three coarse scales in parallel from the low-resolution input and generates only the remaining fine scales autoregressively, reducing hallucination while staying competitive on standard metrics.