Ranking CGANs: Subjective Control over Semantic Image Attributes
This addresses the need for more nuanced control over image generation beyond discrete labels, benefiting applications in creative design and image editing, though it is incremental as it builds on existing CGAN frameworks.
The paper tackles the problem of generating images according to subjective semantic attributes by introducing RankCGAN, which learns to rank images based on subjective measures and uses this to control image generation, demonstrating expressiveness and diversity on datasets like UT-Zap50K, PubFig, and OSR.
In this paper, we investigate the use of generative adversarial networks in the task of image generation according to subjective measures of semantic attributes. Unlike the standard (CGAN) that generates images from discrete categorical labels, our architecture handles both continuous and discrete scales. Given pairwise comparisons of images, our model, called RankCGAN, performs two tasks: it learns to rank images using a subjective measure; and it learns a generative model that can be controlled by that measure. RankCGAN associates each subjective measure of interest to a distinct dimension of some latent space. We perform experiments on UT-Zap50K, PubFig and OSR datasets and demonstrate that the model is expressive and diverse enough to conduct two-attribute exploration and image editing.