CVPR2020

Panoptic-Based Image Synthesis

Aysegul Dundar, Karan Sapra, Guilin Liu, Andrew Tao, Bryan Catanzaro

摘要

Panoptic maps Baseline Ours Ours enlarged Baseline enlarged Figure 1. Unlike previous methods that rely on semantic and boundary label maps to synthesize images, our model uses panoptic maps. It generates instances with clear separation even in cluttered scenes where multiple instances occlude each other. The forth and fifth column show zoomed in patches from the second and third column images to highlight the boundaries between instances, where previous methods tend to blend instances together.