Controllable and Progressive Image Extrapolation
This work addresses the need for controllable content generation in image extrapolation, which is incremental as it builds on existing models by adding text guidance and a multi-stage approach.
The paper tackles the problem of controllable image extrapolation by synthesizing new images guided by structured text represented as a graph, achieving more controllable results through a progressive three-stage generative model validated on face and human clothing datasets.
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.