Face Generation Methods

Contents

• Basic Networks
• Face Swap
• Face Reenactment
• Datasets

---

Basic Networks

2022

2021

• [CVPR'21] [pSp] Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation [pytorch]
• [arXiv'21.06] [AttnFlow] Generative Flows with Invertible Attentions
• [arXiv'21.04] [StyleGAN-Inversion] A Simple Baseline for StyleGAN Inversion [web] [pytorch]

2020

• [ICML'20] [AGD] AutoGAN-Distiller: Searching to Compress Generative Adversarial Networks [pytorch]
• [NIPS'20] [ContraGAN] ContraGAN: Contrastive Learning for Conditional Image Generation [tensorflow]
• [NIPS'20] [CircleGAN] CircleGAN: Generative Adversarial Learning across Spherical Circles [tensorflow]
• [NIPS'20] [DeepI2I] DeepI2I: Enabling Deep Hierarchical Image-to-Image Translation by Transferring from GANs [pytorch]
• [NIPS'20] [NVAE] NVAE: A Deep Hierarchical Variational Autoencoder [pytorch]
• [NIPS'20] [Swapping-Autoencoder] Swapping Autoencoder for Deep Image Manipulation [web] [pytorch]
• [ECCV'20] [COCO-FUNIT] COCO-FUNIT: Few-Shot Unsupervised Image Translation with a Content Conditioned Style Encoder [web] [pytorch]
• [ECCV'20] [TopologyGAN] TopologyGAN: Topology Optimization Using Generative Adversarial Networks Based on Physical Fields Over the Initial Domain [pytorch]
• [ECCV'20] [wc-Vid2Vid] World-Consistent Video-to-Video Synthesis [web] [pytorch]
• [CVPR'20] [StarGAN2] StarGAN v2: Diverse Image Synthesis for Multiple Domains [pytorch]

2019

• [NeurIPS'19] [fs-Vid2Vid] Few-shot Video-to-Video Synthesis [web] [pytorch]
• [ICCV'19] [FUNIT] Few-Shot Unsupervised Image-to-Image Translation [web] [pytorch]
• [CVPR'19] [SPADE] Semantic Image Synthesis with Spatially-Adaptive Normalization [web] [pytorch]

2018

• [NeurIPS'18] [Glow] Glow: Generative Flow with Invertible 1x1 Convolutions [pytorch] [tensorflow]
• [NeurIPS'18] [Vid2Vid] Video-to-Video Synthesis [web] [pytorch]
• [CVPR'18] [StarGAN] StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation [pytorch]
• [CVPR'18] [Pix2PixHD] High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs [web] [pytorch]
• [ECCV'18] [MUNIT] Multimodal Unsupervised Image-to-Image Translation [pytorch]
• [NeurIPS'17] [UNIT] Unsupervised Image-to-Image Translation Networks [pytorch]

2017

• [ICCV'17] [CycleGAN] Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks [web] [pytorch]
• [CVPR'17] [Pix2Pix] Image-to-Image Translation with Conditional Adversarial Networks [web] [pytorch]

---

Face Swap

2022

• [PAMI'22][FSGANv2] FSGANv2: Improved Subject Agnostic Face Swapping and Reenactment

2021

• [IJCAI'21] [HifiFace] HifiFace: 3D Shape and Semantic Prior Guided High Fidelity Face Swapping [home] [unofficial pytorch]
• [CVPR'21] [HFaceInpainter] HFaceInpainter: High Fidelity Face Adaptation to Heterogeneous Domains
• [CVPR'21] [MegaFS] One Shot Face Swapping on Megapixels [] [pytorch]

2020

• [CVPR'20] [Faceshifter] FaceShifter: Towards High Fidelity And Occlusion Aware Face Swapping [home][unoffical pytorch]
• [SIGGRAPH'20] [IDDis] Face Identity Disentanglement via Latent Space Mapping [pytorch]
• [AAAI'20] [Facecontroller] FaceController: Controllable Attribute Editing for Face in the Wild
• [ACCV'20] [UnifiedSR] Unified Application of Style Transfer for Face Swapping and Reenactment
• [ACM'20] [SimSwap] SimSwap: An Efficient Framework For High Fidelity Face Swapping [pytorch]
• [arXiv'20] [DeepFaceLab] DeepFaceLab: Integrated, flexible and extensible face-swapping framework

2019

• [ICCV'19] [FSGAN] FSGAN: Subject Agnostic Face Swapping and Reenactment [pytorch]

2018

• [arXiv'18] [RSGAN] RSGAN: Face Swapping and Editing using Face and Hair Representation in Latent Spaces
• [CVPR'18] [OIPFS] Towards Open-Set Identity Preserving Face Synthesis
• [CVPR'18] [IPNet] Towards Open-Set Identity Preserving Face Synthesis
• [ACCV'18] [FSNet] FSNet: An Identity-Aware Generative Model for Image-based Face Swapping [web]

---

Face Reenactment

2022

• [arXiv'22] [StyleHEAT] StyleHEAT: One-Shot High-Resolution Editable Talking Face Generation via Pre-trained StyleGAN [home] [code]
• [ICLR'22] [LIA]Latent Image Animator: Learning to Animate Images via Latent Space Navigation [home]
• [CVPR'22] [DuGAN] Depth-Aware Generative Adversarial Network for Talking Head Video Generation [home] [pytorch]

2021

• [3DV'21] [SAFA] SAFA: Structure Aware Face Animation [pytorch]
• [CVPR'21] [MRAA] Motion Representations for Articulated Animation [home] [pytorch]
• [CVPR'21] [face-vid2vid] One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing [web]
• [ICCV'21] [HeadGAN] HeadGAN: One-shot Neural Head Synthesis and Editing [home] [video]
• [ICCV'21] [PIRenderer] PIRenderer: Controllable Portrait Image Generation via Semantic Neural Rendering [home] [video] [pytorch]

2020

• [CVPR'20] [FReeNet] FReeNet: Multi-Identity Face Reenactment [pytorch]
• [ICASSP'20] [APB2Face] APB2Face: Audio-guided face reenactment with auxiliary pose and blink signals [pytorch]
• [ECCV'20] [Bi-layer] Fast Bi-layer Neural Synthesis of One-Shot Realistic Head Avatars [pytorch]
• [CVPRW'20] [FaR-GAN] FaR-GAN for One-Shot Face Reenactment
• [AAAI'20] [DAE-GAN] Realistic Face Reenactment via Self-Supervised Disentangling of Identity and Pose

2019

• [NIPS'19] [FOMM] First Order Motion Model for Image Animation [web] [pytorch]
• [BMVC'19] [OSFR] One-shot Face Reenactment [home] [pytorch]

2018

• [ECCV'18] [X2Face] X2Face: A network for controlling face generation by using images, audio, and pose codes [pytorch]
• [ECCV'18] [ReenactGAN] ReenactGAN: Learning to Reenact Faces via Boundary Transfer [pytorch]

---

Datasets

• [CelebA]
• [CelebA-HQ]
• [CelebAMask-HQ]
• [CelebA-Spoof]
• [FFHQ]
• [VoxCeleb1]
• [VoxCeleb2]
• [VGGFace]
• [VGGFace2]
• [RaFD]
• [Multi-PIE]
• [FaceForensics++][**1000 HifiFace FaceForensics++ **]
• [SCUT-FBP]
• [MakeUp]

---

Borrow and Thanks for these repos awesome-face-generation, Human Video Generation, awesome-faceReenactment