Proposes generative guiding blocks with appearance-preserving and variation-transforming discriminators to enable realistic image synthesis under large change demands in generative models.
Datasets For verifying the effectiveness of the proposed generative model with GGBs, we used public datasets: DeepFash- ion [22]
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Generative Guiding Block: Synthesizing Realistic Looking Variants Capable of Even Large Change Demands
Proposes generative guiding blocks with appearance-preserving and variation-transforming discriminators to enable realistic image synthesis under large change demands in generative models.