Controllable And Progressive Image Extrapolation
2021 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION WACV 2021(2021)
摘要
Image extrapolation aims at expanding the narrow field of view of a given image patch. Existing models mainly deal with natural scene images of homogeneous regions and have no control of the content generation process. In this work, we study conditional image extrapolation to synthesize new images guided by the input structured text. The text is represented as a graph to specify the objects and their spatial relation to the unknown regions of the image. Inspired by drawing techniques, we propose a progressive generative model of three stages, i.e., generating a coarse bounding-boxes layout, refining it to a finer segmentation layout, and mapping the layout to a realistic output. Such a multi-stage design is shown to facilitate the training process and generate more controllable results. We validate the effectiveness of the proposed method on the face and human clothing dataset in terms of visual results, quantitative evaluations, and flexible controls.
更多查看译文
关键词
conditional image extrapolation,input structured text,spatial relation,unknown regions,drawing techniques,progressive generative model,coarse bounding-boxes layout,finer segmentation layout,multistage design,training process,controllable results,flexible controls,progressive image extrapolation,given image patch,natural scene images,homogeneous regions,content generation process
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络