A progressive face super-resolution network with a landmark-heatmap-weighted attention loss produces 8x upscaled faces that human raters judged more realistic than prior methods.
Wasserstein generative adversarial net- works
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Progressive Face Super-Resolution via Attention to Facial Landmark
A progressive face super-resolution network with a landmark-heatmap-weighted attention loss produces 8x upscaled faces that human raters judged more realistic than prior methods.