SC-FEGAN: Face Editing Generative Adversarial Network with User's Sketch and Color

TL;DR

This paper introduces SC-FEGAN, a convolutional network that enables realistic face editing by incorporating free-form user sketches and colors, allowing intuitive and high-quality image modifications.

Contribution

The novel SC-FEGAN architecture effectively utilizes user sketches and colors for face editing, improving realism and responsiveness compared to prior methods.

Findings

Generated realistic face images with user sketches and colors

Achieved high-quality results despite large image modifications

Enhanced image realism using style loss during training

Abstract

We present a novel image editing system that generates images as the user provides free-form mask, sketch and color as an input. Our system consist of a end-to-end trainable convolutional network. Contrary to the existing methods, our system wholly utilizes free-form user input with color and shape. This allows the system to respond to the user's sketch and color input, using it as a guideline to generate an image. In our particular work, we trained network with additional style loss which made it possible to generate realistic results, despite large portions of the image being removed. Our proposed network architecture SC-FEGAN is well suited to generate high quality synthetic image using intuitive user inputs.