Generative Adversarial Network Inversion

Generative Adversarial Network (GAN) inversion aims to find the latent code within a pre-trained GAN that best represents a given real-world image, enabling image editing and manipulation without retraining the GAN. Current research focuses on improving the fidelity of the inversion process, often employing techniques like domain-guided encoders, optimization strategies tailored to the GAN's latent space, and methods to handle out-of-domain regions in the input image. This field is significant for its applications in diverse areas such as image inpainting, data augmentation for medical imaging, and privacy-preserving techniques for biometric data, offering powerful tools for image editing and analysis.

Papers

March 18, 2024

E2F-Net: Eyes-to-Face Inpainting via StyleGAN Latent Space
Ahmad Hassanpour, Fatemeh Jamalbafrani, Bian Yang, Kiran Raja, Raymond Veldhuis, Julian Fierrez
Generative Adversarial Network StyleGAN Latent Face Segmentation Face to Face Generative Adversarial Network Inversion

September 25, 2023

In-Domain GAN Inversion for Faithful Reconstruction and Editability
Jiapeng Zhu, Yujun Shen, Yinghao Xu, Deli Zhao, Qifeng Chen, Bolei Zhou
Generative Adversarial Network GAN Model GAN Inversion Accurate Reconstruction Editing Capability Generative Adversarial Network Inversion

July 5, 2023

Generative Adversarial Networks for Dental Patient Identity Protection in Orthodontic Educational Imaging
Mingchuan Tian, Wilson Weixun Lu, Kelvin Weng Chiong Foong, Eugene Loh
Generative Adversarial Network Generative Adversarial Network Inversion

May 18, 2023

JoIN: Joint GANs Inversion for Intrinsic Image Decomposition
Viraj Shah, Svetlana Lazebnik, Julien Philip
Generative Adversarial Network GAN Model Inverse Problem GAN Inversion Intrinsic Image Decomposition Generative Adversarial Network Inversion

April 12, 2023

On the Adversarial Inversion of Deep Biometric Representations
Gioacchino Tangari, Shreesh Keskar, Hassan Jameel Asghar, Dali Kaafar
Adversarial Scenario Biometric Data Generative Adversarial Network Inversion

December 19, 2022

Out-of-domain GAN inversion via Invertibility Decomposition for Photo-Realistic Human Face Manipulation
Xin Yang, Xiaogang Xu, Yingcong Chen
Generative Adversarial Network Restricted Approximate Invertibility Generative Adversarial Network Inversion

November 24, 2022

More comprehensive facial inversion for more effective expression recognition
Jiawei Mao, Guangyi Zhao, Yuanqi Chang, Xuesong Yin, Xiaogang Peng, Rui Xu
Facial Expression Recognition Inverse Rendering Facial Datasets Generative Adversarial Network Inversion Complex Facial Expression Recognition

July 17, 2022

Editing Out-of-domain GAN Inversion via Differential Activations
Haorui Song, Yong Du, Tianyi Xiang, Junyu Dong, Jing Qin, Shengfeng He
GAN Model GAN Inversion Real Image Editing Generative Adversarial Network Inversion

May 4, 2022

GAN Inversion for Data Augmentation to Improve Colonoscopy Lesion Classification
Mayank Golhar, Taylor L. Bobrow, Saowanee Ngamruengphong, Nicholas J. Durr
Generative Adversarial Network Data Augmentation Colorectal Cancer Polyp Colonoscopy Data Generative Adversarial Network Inversion

March 21, 2022

High-fidelity GAN Inversion with Padding Space
Qingyan Bai, Yinghao Xu, Jiapeng Zhu, Weihao Xia, Yujiu Yang, Yujun Shen
Generative Adversarial Network GAN Model Image Editing Zero Padding Generative Adversarial Network Inversion

September 14, 2021

High-Fidelity GAN Inversion for Image Attribute Editing
Tengfei Wang, Yong Zhang, Yanbo Fan, Jue Wang, Qifeng Chen
Generative Adversarial Network Image Fidelity High Fidelity Reconstruction Generative Adversarial Network Inversion