Gradient-guided latent space traversal in generative models enables controlled augmentation of iris images that preserve identity while manipulating attributes such as sharpness, pupil size, iris size, or pupil-to-iris ratio.
Conditional wasserstein generative adversarial networks for rebalancing iris image datasets.IEICE TRANSACTIONS on Information and Sys- tems, 104(9):1450–1458
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Gradient-Guided Exploration of Generative Model's Latent Space for Controlled Iris Image Augmentations
Gradient-guided latent space traversal in generative models enables controlled augmentation of iris images that preserve identity while manipulating attributes such as sharpness, pupil size, iris size, or pupil-to-iris ratio.