StoryGAN: A Sequential Conditional GAN for Story Visualization
arXiv:1812.02784
Abstract
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. We therefore 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, 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 outperforms state-of-the-art models in image quality, contextual consistency metrics, and human evaluation.
References in corpus (12)
- Adam: A Method for Stochastic Optimization
- Generative Adversarial Text to Image Synthesis
- NICE: Non-linear Independent Components Estimation
- Universal Sentence Encoder
- Density estimation using Real NVP
- Stochastic Video Generation with a Learned Prior
- Visual Storytelling
- ChatPainter: Improving Text to Image Generation using Dialogue
- Recurrent Topic-Transition GAN for Visual Paragraph Generation
- Hierarchically Structured Reinforcement Learning for Topically Coherent Visual Story Generation
- CoDraw: Collaborative Drawing as a Testbed for Grounded Goal-driven Communication
- Probabilistic Video Generation using Holistic Attribute Control