Generative adversarial networks (GANs) have many application areas including image editing, domain translation, missing data imputation, and support for creative work. However, GANs are considered 'black boxes'. Specifically, the end-users have little control over how to improve editing directions through disentanglement. Prior work focused on new GAN architectures to disentangle editing directions. Alternatively, we propose GANravel a user-driven direction disentanglement tool that complements the existing GAN architectures and allows users to improve editing directions iteratively. In two user studies with 16 participants each, GANravel users were able to disentangle directions and outperformed the state-of-the-art direction discovery baselines in disentanglement performance. In the second user study, GANravel was used in a creative task of creating dog memes and was able to create high-quality edited images and GIFs.
翻译:生成对抗网络( GANs) 有许多应用领域, 包括图像编辑、 域名翻译、 缺少数据估算和支持创造性工作。 然而, GANs 被视为“ 黑盒 ” 。 具体地说, 终端用户对如何通过分解改进编辑方向没有多少控制权。 先前的工作侧重于新的 GAN 结构以解开编辑方向。 或者, 我们提议 GANRAVel 是一个用户驱动的方向解剖工具, 以补充现有的 GAN 结构, 让用户能够迭接地改进编辑方向。 在两次用户研究中, GANRAVel 用户能够分解方向, 并超越最先进的发现方向基线 。 在第二项用户研究中, GANRAVel 被用于创建狗的创造性任务, 并能够创建高质量的编辑图像和 GIFs 。