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

arXiv: https://arxiv.org/abs/2011.01563 · HTML: https://mlsanity.com/paper/2011.01563/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Nov 2020.

## Built on by (most cited first, 8 of 8)

- [A Latent Transformer for Disentangled Face Editing in Images and Videos](https://mlsanity.com/paper/2106.11895/) (2021)
- [High-Fidelity and Arbitrary Face Editing](https://mlsanity.com/paper/2103.15814/) (2021)
- [GAN-based Facial Attribute Manipulation](https://mlsanity.com/paper/2210.12683/) (2022)
- [Toward Tiny and High-quality Facial Makeup with Data Amplify Learning](https://mlsanity.com/paper/2403.15033/) (2024)
- [Training and Tuning Generative Neural Radiance Fields for Attribute-Conditional 3D-Aware Face Generation](https://mlsanity.com/paper/2208.12550/) (2022)
- [Unsupervised High-Resolution Portrait Gaze Correction and Animation](https://mlsanity.com/paper/2207.00256/) (2022)
- [A comprehensive survey on semantic facial attribute editing using generative adversarial networks](https://mlsanity.com/paper/2205.10587/) (2022)
- [CCR: Facial Image Editing with Continuity, Consistency and Reversibility](https://mlsanity.com/paper/2209.10734/) (2022)

## Abstract (arXiv)

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.