Design What You Desire: Icon Generation from Orthogonal Application and Theme Labels
This work addresses a domain-specific business need for automated icon generation, representing an incremental improvement with a novel method for a known bottleneck.
The paper tackles the problem of generating customizable icons for mobile applications with specific theme styles, proposing IconGAN to address mode collapse in StyleGAN2 caused by entangled orthogonal labels, achieving superior performance on the AppIcon benchmark.
Generative adversarial networks (GANs) have been trained to be professional artists able to create stunning artworks such as face generation and image style transfer. In this paper, we focus on a realistic business scenario: automated generation of customizable icons given desired mobile applications and theme styles. We first introduce a theme-application icon dataset, termed AppIcon, where each icon has two orthogonal theme and app labels. By investigating a strong baseline StyleGAN2, we observe mode collapse caused by the entanglement of the orthogonal labels. To solve this challenge, we propose IconGAN composed of a conditional generator and dual discriminators with orthogonal augmentations, and a contrastive feature disentanglement strategy is further designed to regularize the feature space of the two discriminators. Compared with other approaches, IconGAN indicates a superior advantage on the AppIcon benchmark. Further analysis also justifies the effectiveness of disentangling app and theme representations. Our project will be released at: https://github.com/architect-road/IconGAN.