Exploring the Effectiveness of Mask-Guided Feature Modulation as a Mechanism for Localized Style Editing of Real Images
This work addresses bottlenecks in style editing for image generation applications, though it appears incremental as it builds on existing deep generative models.
The paper tackles the computational expense and human supervision required for style editing of real images by introducing the SemanticStyle Autoencoder (SSAE), which uses mask-guided feature modulation to achieve highly localized photorealistic edits.
The success of Deep Generative Models at high-resolution image generation has led to their extensive utilization for style editing of real images. Most existing methods work on the principle of inverting real images onto their latent space, followed by determining controllable directions. Both inversion of real images and determination of controllable latent directions are computationally expensive operations. Moreover, the determination of controllable latent directions requires additional human supervision. This work aims to explore the efficacy of mask-guided feature modulation in the latent space of a Deep Generative Model as a solution to these bottlenecks. To this end, we present the SemanticStyle Autoencoder (SSAE), a deep Generative Autoencoder model that leverages semantic mask-guided latent space manipulation for highly localized photorealistic style editing of real images. We present qualitative and quantitative results for the same and their analysis. This work shall serve as a guiding primer for future work.