Publications

Collaging Class-specific GANs for Semantic Image Synthesis

International Conference on Computer Vision (ICCV'21)

Published October 13, 2021

Yuheng Li, Yijun Li, Jingwan (Cynthia) Lu, Eli Shechtman, Yong Jae Lee, Krishna Kumar Singh, Jingwan (Cynthia) Lu

We propose a new approach for high resolution semantic image synthesis. It consists of one base image generator and multiple class-specific generators. The base generator generates high quality images based on a segmentation map. To further improve the quality of different objects, we create a bank of Generative Adversarial Networks (GANs) by separately training class-specific models. This has several benefits including -- dedicated weights for each class; centrally aligned data for each model; additional training data from other sources, potential of higher resolution and quality; and easy manipulation of a specific object in the scene. Experiments show that our approach can generate high quality images in high resolution while having flexibility of object-level control by using class-specific generators.

Learn More