LLV-FSR adds caption, description, semantic-mask, and depth priors from large pretrained models into a face super-resolution network and reports state-of-the-art PSNR on MMCelebA-HQ.
Chan, Xiangyu Xu, Xintao Wang, Jinwei Gu, and Chen Change Loy
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
LLV-FSR: Exploiting Large Language-Vision Prior for Face Super-resolution
LLV-FSR adds caption, description, semantic-mask, and depth priors from large pretrained models into a face super-resolution network and reports state-of-the-art PSNR on MMCelebA-HQ.