ChatPainter: Improving Text to Image Generation using Dialogue
Synthesizing realistic images from text descriptions on a dataset like Microsoft Common Objects in Context (MS COCO), where each image can contain several objects, is a challenging task. Prior work has used text captions to generate images. However, captions might not be informative enough to capture the entire image and insufficient for the model to be able to understand which objects in the images correspond to which words in the captions. We show that adding a dialogue that further describes the scene leads to significant improvement in the inception score and in the quality of generated images on the MS COCO dataset.
PDF Abstract
CIFAR-10
ImageNet
MS COCO
MNIST
Oxford 102 Flower
VisDial
Results from the Paper
Ranked #25 on
Text-to-Image Generation
on MS COCO
(Inception score metric)
