leicagan
Learn, Imagine and Create: Text-to-Image Generation from Prior Knowledge
Tingting Qiao, Jing Zhang, Duanqing Xu, Dacheng Tao
Given a text description, we immediately imagine an overall visual impression using this prior and, based on this, we draw a picture by progressively adding more andmore details.
- Oceania > Australia (0.04)
- North America > Canada > British Columbia > Metro Vancouver Regional District > Vancouver (0.04)
- Europe > Italy > Calabria > Catanzaro Province > Catanzaro (0.04)
- Asia > China (0.04)
Learn, Imagine and Create: Text-to-Image Generation from Prior Knowledge
Text-to-image generation, i.e. generating an image given a text description, is a very challenging task due to the significant semantic gap between the two domains. Humans, however, tackle this problem intelligently. We learn from diverse objects to form a solid prior about semantics, textures, colors, shapes, and layouts. Given a text description, we immediately imagine an overall visual impression using this prior and, based on this, we draw a picture by progressively adding more and more details. In this paper, and inspired by this process, we propose a novel text-to-image method called LeicaGAN to combine the above three phases in a unified framework.
Learn, Imagine and Create: Text-to-Image Generation from Prior Knowledge
Tingting Qiao, Jing Zhang, Duanqing Xu, Dacheng Tao
Humans, however, tackle this problem intelligently.
- Asia > China > Zhejiang Province (0.04)
- Oceania > Australia (0.04)
- North America > United States > California (0.04)
- (2 more...)
Learn, Imagine and Create: Text-to-Image Generation from Prior Knowledge
Text-to-image generation, i.e. generating an image given a text description, is a very challenging task due to the significant semantic gap between the two domains. Humans, however, tackle this problem intelligently. We learn from diverse objects to form a solid prior about semantics, textures, colors, shapes, and layouts. Given a text description, we immediately imagine an overall visual impression using this prior and, based on this, we draw a picture by progressively adding more and more details. In this paper, and inspired by this process, we propose a novel text-to-image method called LeicaGAN to combine the above three phases in a unified framework.
Learn, Imagine and Create: Text-to-Image Generation from Prior Knowledge
Qiao, Tingting, Zhang, Jing, Xu, Duanqing, Tao, Dacheng
Text-to-image generation, i.e. generating an image given a text description, is a very challenging task due to the significant semantic gap between the two domains. Humans, however, tackle this problem intelligently. We learn from diverse objects to form a solid prior about semantics, textures, colors, shapes, and layouts. Given a text description, we immediately imagine an overall visual impression using this prior and, based on this, we draw a picture by progressively adding more and more details. In this paper, and inspired by this process, we propose a novel text-to-image method called LeicaGAN to combine the above three phases in a unified framework.