Cookgan: Causality Based Text-To-Image Synthesis
2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)(2020)
摘要
This paper addresses the problem of text-to-image synthesis from a new perspective, i.e., the cause-and-effect chain in image generation. Causality is a common phenomenon in cooking. The dish appearance changes depending on the cooking actions and ingredients. The challenge of synthesis is that a generated image should depict the visual result of action-on-object. This paper presents a new network architecture, CookGAN, that mimics visual effect in causality chain, preserves fine-grained details and progressively upsamples image. Particularly, a cooking simulator sub-network is proposed to incrementally make changes to food images based on the interaction between ingredients and cooking methods over a series of steps. Experiments on Recipe1M verify that CookGAN manages to generate food images with reasonably impressive inception score. Furthermore, the images are semantically interpretable and manipulable.
更多查看译文
关键词
text-to-image synthesis,image generation,dish appearance changes,cooking actions,action-on-object,CookGAN,causality chain,image upsampling,cooking simulator sub-network,food images,cause-and-effect chain
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要