DeepFacePencil: Creating Face Images from Freehand Sketches
This addresses the challenge of creating realistic face images from freehand sketches for applications in art, design, or forensics, but it is incremental as it builds on image-to-image translation methods.
The paper tackles the problem of generating photo-realistic face images from hand-drawn sketches, which existing methods struggle with due to limited generalization to diverse stroke styles. The proposed DeepFacePencil model demonstrates superiority over existing methods in image quality and generalization to hand-drawn sketches.
In this paper, we explore the task of generating photo-realistic face images from hand-drawn sketches. Existing image-to-image translation methods require a large-scale dataset of paired sketches and images for supervision. They typically utilize synthesized edge maps of face images as training data. However, these synthesized edge maps strictly align with the edges of the corresponding face images, which limit their generalization ability to real hand-drawn sketches with vast stroke diversity. To address this problem, we propose DeepFacePencil, an effective tool that is able to generate photo-realistic face images from hand-drawn sketches, based on a novel dual generator image translation network during training. A novel spatial attention pooling (SAP) is designed to adaptively handle stroke distortions which are spatially varying to support various stroke styles and different levels of details. We conduct extensive experiments and the results demonstrate the superiority of our model over existing methods on both image quality and model generalization to hand-drawn sketches.