Sketch to Image Synthesis

Sketch to Image Synthesis

    Presenter(s)

    Samah Saeed A Baraheem

    Comments

    Presentation: 9:00-9:20 p.m., Jessie Hathcock Hall 180

    Description

    Sketch-to-image is an important task to reduce the burden of creating a color image from scratch. Unlike previous sketch-to-image models, where the image is synthesized in an end-to-end manner, leading to an unnaturalistic image, we propose a method by decomposing the problem into subproblems to generate a more naturalistic and reasonable image. It first generates an intermediate output which is a semantic mask map from the input sketch through instance and semantic segmentation in two levels, background segmentation and foreground segmentation. Background segmentation is formed based on the context of the foreground objects. Then, the foreground segmentations are sequentially added to the created background segmentation. Finally, the generated mask map is fed into an image-to-image translation model to generate an image. Our proposed method works with 92 distinct classes. Compared to state-of-the-art sketch-to-image models, our proposed method outperforms the previous methods and generates better images.

    Publication Date

    4-19-2023

    Project Designation

    Graduate Research

    Primary Advisor

    Van Nguyen

    Primary Advisor's Department

    Computer Science

    Keywords

    Stander Symposium, College of Arts and Sciences

    Institutional Learning Goals

    Scholarship

    Sketch to Image Synthesis

    Share

    COinS