CooGAN: A Memory-Efficient Framework for High-Resolution Facial Attribute Editing

TL;DR

CooGAN is a novel, memory-efficient framework for high-resolution facial attribute editing that combines local patch generation and global structure monitoring, enabling high-quality editing with limited memory.

Contribution

This paper introduces CooGAN, a new pixel translation framework that reduces memory usage for high-resolution face editing through a cooperative local-global architecture and efficient feature fusion.

Findings

Demonstrates high-quality high-resolution facial editing with limited memory

Achieves superior memory efficiency compared to existing methods

Produces high-fidelity facial attribute manipulations

Abstract

In contrast to great success of memory-consuming face editing methods at a low resolution, to manipulate high-resolution (HR) facial images, i.e., typically larger than 7682 pixels, with very limited memory is still challenging. This is due to the reasons of 1) intractable huge demand of memory; 2) inefficient multi-scale features fusion. To address these issues, we propose a NOVEL pixel translation framework called Cooperative GAN(CooGAN) for HR facial image editing. This framework features a local path for fine-grained local facial patch generation (i.e., patch-level HR, LOW memory) and a global path for global lowresolution (LR) facial structure monitoring (i.e., image-level LR, LOW memory), which largely reduce memory requirements. Both paths work in a cooperative manner under a local-to-global consistency objective (i.e., for smooth stitching). In addition, we propose a lighter selective transfer unit for more efficient multi-scale features fusion, yielding higher fidelity facial attributes manipulation. Extensive experiments on CelebAHQ well demonstrate the memory efficiency as well as the high image generation quality of the proposed framework.