GeoMAR combines dual-input VLM text priors and MaskGIT-style iterative code prediction for blind face restoration, posting modest perceptual gains on real-world face benchmarks.
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
-
GeoMAR: Unleashing Geometrically Aligned Features for Masked Autoregressive Blind Face Restoration
GeoMAR combines dual-input VLM text priors and MaskGIT-style iterative code prediction for blind face restoration, posting modest perceptual gains on real-world face benchmarks.