Cali-Sketch: Stroke Calibration and Completion for High-Quality Face Image Generation from Human-Like Sketches

TL;DR

Cali-Sketch introduces a two-step approach for high-quality face image generation from human-like sketches, effectively calibrating strokes and synthesizing realistic images even with poorly aligned sketches.

Contribution

The paper proposes Cali-Sketch, a novel method that explicitly models stroke calibration and image synthesis, improving face image quality from imperfect sketches.

Findings

Generated face images are more photo-realistic and faithful to sketches.

Cali-Sketch outperforms state-of-the-art methods in quality and fidelity.

Decoupling calibration and synthesis simplifies cross-domain translation.

Abstract

Image generation has received increasing attention because of its wide application in security and entertainment. Sketch-based face generation brings more fun and better quality of image generation due to supervised interaction. However, when a sketch poorly aligned with the true face is given as input, existing supervised image-to-image translation methods often cannot generate acceptable photo-realistic face images. To address this problem, in this paper we propose Cali-Sketch, a human-like-sketch to photo-realistic-image generation method. Cali-Sketch explicitly models stroke calibration and image generation using two constituent networks: a Stroke Calibration Network (SCN), which calibrates strokes of facial features and enriches facial details while preserving the original intent features; and an Image Synthesis Network (ISN), which translates the calibrated and enriched sketches to photo-realistic face images. In this way, we manage to decouple a difficult cross-domain translation problem into two easier steps. Extensive experiments verify that the face photos generated by Cali-Sketch are both photo-realistic and faithful to the input sketches, compared with state-of-the-art methods.