StoryGAN: A Sequential Conditional GAN for Story Visualization

Authors:
  • YLYitong Li
    Yitong Li
  • ZGZhe Gan
    Zhe Gan
  • YSYelong Shen
    Yelong Shen
  • JLJingjing Liu
    Jingjing Liu
  • YCYu Cheng
    Yu Cheng
  • YWYuexin Wu
    Yuexin Wu
  • LCLawrence Carin
    Lawrence Carin
  • DCDavid Carlson
    David Carlson
  • JGJianfeng Gao
    Jianfeng Gao
Preprint
Publisher website
Google Scholar
Abstract
In this work we propose a new task called Story Visualization. Given a multi-sentence paragraph, the story is visualized by generating a sequence of images, one for each sentence. In contrast to video generation, story visualization focuses less on the continuity in generated images (frames), but more on the global consistency across dynamic scenes and characters -- a challenge that has not been addressed by any single-image or video generation methods. Therefore, we propose a new story-to-image-sequence generation model, StoryGAN, based on the sequential conditional GAN framework. Our model is unique in that it consists of a deep Context Encoder that dynamically tracks the story flow, and two discriminators at the story and image levels, respectively, to enhance the image quality and the consistency of the generated sequences. To evaluate the model, we modified existing datasets to create the CLEVR-SV and Pororo-SV datasets. Empirically, StoryGAN outperformed state-of-the-art models in image quality, contextual consistency metrics, and human evaluation.

This publication has 21 references indexed in Scilit: