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.
InProceedings of the 33rd ACM International Conference on Multimedia
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
baseline 1
citation-polarity summary
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1roles
baseline 1polarities
unclear 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.