PLDGAN: portrait line drawing generation with prior knowledge and conditioning target

Sifei Li

Abstract: Line drawing, a form of minimalist art, is highly abstract and expressive with practical use in conveying 3D shapes and indicating object occlusion. Generating line drawings from photographs is a challenging task that requires the compression of rich texture information into sparse geometric elements, such as lines, curves, and circles, without compromising semantic information. Furthermore, a portrait line drawing should include a full human silhouette and important semantic lines of scenes while avoiding messy lines. To address those challenges, we propose a novel method for generating portrait line drawings, named PLDGAN (Portrait Line Drawing Generative Adversarial Network), which utilizes prior knowledge of pose and semantic segmentation information. We also design a conditioning target and adjust the content loss to the original target loss. To train our PLDGAN, we collect a new dataset containing pairwise portrait images and professional portrait line drawings. Our experiments show that our proposed method achieves state-of-the-art performance and can generate high-quality portrait line drawings.