Content-Conditioned Generation of Stylized Free hand Sketches
This work addresses the difficulty of large-scale sampling and style variation in free-hand sketches for recognition and segmentation tasks, particularly in specialized domains, though it appears incremental as it builds on existing generative adversarial networks.
The paper tackles the problem of generating realistic free-hand sketches with various styles, which is challenging due to limited data in fields like the military, and proposes an adversarial generative network that achieves high visual quality, content accuracy, and style imitation as demonstrated on the SketchIME dataset.
In recent years, the recognition of free-hand sketches has remained a popular task. However, in some special fields such as the military field, free-hand sketches are difficult to sample on a large scale. Common data augmentation and image generation techniques are difficult to produce images with various free-hand sketching styles. Therefore, the recognition and segmentation tasks in related fields are limited. In this paper, we propose a novel adversarial generative network that can accurately generate realistic free-hand sketches with various styles. We explore the performance of the model, including using styles randomly sampled from a prior normal distribution to generate images with various free-hand sketching styles, disentangling the painters' styles from known free-hand sketches to generate images with specific styles, and generating images of unknown classes that are not in the training set. We further demonstrate with qualitative and quantitative evaluations our advantages in visual quality, content accuracy, and style imitation on SketchIME.