Paint-your-mind II: stylistic image creation by concept

• Main Author: Wang, Anyi
• Other Authors: Cham Tat Jen
• Format: Final Year Project
• Language: English
• Published: Nanyang Technological University 2023
• Subjects: Engineering::Computer science and engineering
• Online Access: https://hdl.handle.net/10356/166172
• Institution: Nanyang Technological University

This report presents a novel approach to generate stylistic paintings from segmentation maps. The proposed method utilizes various image-to-image translation techniques, including artistic style transfer and image enhancement, to generate visually appealing and diverse paintings. The results of the experiments show that the proposed method is able to generate paintings that are structurally similar to the input semantic maps, while also incorporating the desired style. A web platform is also developed as part of this project to enable such computer vision techniques to be accessible to the masses in an interactive way. This research has the potential to be applied in a variety of fields such as computer graphics, virtual reality, digital art, or creating convincing prototypes for these tasks.