There are 4 repositories under face-editing topic.
[SIGGRAPH Asia 2022] IDE-3D: Interactive Disentangled Editing For High-Resolution 3D-aware Portrait Synthesis
[ICCV 2023] StyleGANEX: StyleGAN-Based Manipulation Beyond Cropped Aligned Faces
Collaborative Diffusion (CVPR 2023)
AttGAN PyTorch Arbitrary Facial Attribute Editing: Only Change What You Want
Various applications based on Stylegan2 Style mixing that can be inference on cpu.
[ECCV 2020] "Deep Plastic Surgery: Robust and Controllable Image Editing with Human-Drawn Sketches"
InterfaceGAN++: Exploring the limits of InterfaceGAN. In this repository, we propose an approach, termed as InterFaceGAN++, for semantic face editing based on the work from Shen et al. Specifically, we leverage the ideas from the previous work, by applying the method for new face attributes, and also for StyleGAN3. We qualitatively explain that moving the latent vector toward the trained boundaries leads in many cases to keeping the semantic information of the generated images (by preserving its local structure) and modify the desired attribute, thus helps to demonstrate the disentangled property of the StyleGANs.
Re-implementation of e4e that use mobilenet-v3 and stylegan2-1024p
Face attribute manipulation with GAN for automatic data augmentation or individual editing.
Re-implementation of pSp that use mobilenet-v3 and stylegan2-256p
a simple pipeline for face editing
Diverse Facial Edit with StyleGAN, StyleGAN2, StyleClip with ViT, and Other Features like Background Removal and Face Swap
[ECCV 2020] Deep Plastic Surgery: Robust and Controllable Image Editing with Human-Drawn Sketches
Presentation and Report (Extended abstract) for a selected paper created during Computer vision seminar (MA-INF 2206).
The project focuses on manipulating facial features by adjusting the latent vectors within StyleGAN's architecture. Our objective is to achieve precise modifications in age, gender, and facial expressions in generated images.