Gan Pei * . Jiangning Zhang * . Menghan Hu . Zhenyu Zhang . Chengjie Wang . Yunsheng Wu.
Guangtao Zhai . Jian Yang . Chunhua Shen . Dacheng Tao
This work focuses on the aspect of facial manipulation in Deepfake, encompassing Face swapping, Face reenactment, Talking Face Generation, Face attribute editing and Forgery Detection. We believe this will be the most comprehensive survey to date on facial manipulation and detection technologies. Please stay tuned!😉😉😉
✨You are welcome to provide us your work with a topic related to deepfake generation or detection!!!
If you discover any missing work or have any suggestions, please feel free to submit a pull request or contact us. We will promptly add the missing papers to this repository.
[1] A comprehensive survey for visual Deepfake, including Deepfake generation/detection.
[2] It also contains several related domains, including Heas Swapping, Face Super-resolution, Face Reconstruction, Face Inpainting, Body Animation, Portrait Style Transfer, Makeup Transfer and Adversarial Sample Detection.
[3] We list detailed results for the most representative works.
This survey presents a detailed survey on generation and detection tasks about face-related generation, including Face swap, Face reenactment, Talking Face Generation, and Face attribute editing. In addition, we also introduce several related fields such as Head Swap, Face Super-resolution, Face Reconstruction, Face Inpainting, etc., and select some of them to expand.
| Year | Venue | Category | Paper Title | Code |
|---|---|---|---|---|
| 2024 | arXiv | 3DGS | ImplicitDeepfake: Plausible Face-Swapping through Implicit Deepfake Generation using NeRF and Gaussian Splatting | Code |
| 2024 | arXiv | GANs | LatentSwap: An Efficient Latent Code Mapping Framework for Face Swapping | - |
| 2024 | arXiv | VAEs | SelfSwapper: Self-Supervised Face Swapping via Shape Agnostic Masked AutoEncoder | - |
| 2024 | arXiv | Difussion | Face Swap via Diffusion Model | - |
| 2024 | arXiv | Difussion | Towards a Simultaneous and Granular Identity-Expression Control in Personalized Face Generation | Code |
| 2024 | arXiv | GANs | E4S: Fine-grained Face Swapping via Editing With Regional GAN Inversion | Code |
| 2024 | ICIP | Graphic | RID-TWIN: An end-to-end pipeline for automatic face de-identification in videos | Code |
| 2024 | TCSVT | VAE | Identity-Aware Variational Autoencoder for Face Swapping | - |
| 2024 | ICASSP | GANs+3D | Attribute-Aware Head Swapping Guided by 3d Modeling | - |
| 2024 | TMM | Other | An Efficient Attribute-Preserving Framework for Face Swapping | - |
| 2024 | TMM | GANs+3D | StableSwap: Stable Face Swapping in a Shared and Controllable Latent Space | - |
| 2023 | arXiv | GANs | FlowFace++: Explicit Semantic Flow-supervised End-to-End Face Swapping | - |
| 2023 | WACV | VAEs | FaceOff: A Video-to-Video Face Swapping System | - |
| 2023 | CVPR | GANs+3DMM | StyleIPSB: Identity-Preserving Semantic Basis of StyleGAN for High Fidelity Face Swapping | Code |
| 2023 | CVPR | GANs+3DMM | 3D-Aware Face Swapping | Code |
| 2023 | CVPR | GANs | Fine-Grained Face Swapping via Regional GAN Inversion | Code |
| 2023 | WACV | GANs | FastSwap: A Lightweight One-Stage Framework for Real-Time Face Swapping | Code |
| 2023 | TECS | GANs+VAEs | XimSwap: many-to-many face swapping for TinyML | - |
| 2023 | WACV | GANs | FaceDancer: Pose- and Occlusion-Aware High Fidelity Face Swapping | Code |
| 2023 | ICCV | GANs | BlendFace: Re-designing Identity Encoders for Face-Swapping | Code |
| 2023 | ICCV | GANs+3DMM | Reinforced Disentanglement for Face Swapping without Skip Connection | - |
| 2023 | CVPR | GANs | Attribute-preserving Face Dataset Anonymization via Latent Code Optimizatio | Code |
| 2023 | AAAI | GANs+3DMM | FlowFace: Semantic Flow-Guided Shape-Aware Face Swapping | - |
| 2023 | CVPR | Transformers | Face Transformer: Towards High Fidelity and Accurate Face Swapping | - |
| 2023 | ACM MM | GANs+3D | High Fidelity Face Swapping via Semantics Disentanglement and Structure Enhancement | - |
| 2023 | arXiv | GANs | End-to-end Face-swapping via Adaptive Latent Representation Learning | - |
| 2023 | FG | Transformers | TransFS: Face Swapping Using Transformer | - |
| 2023 | arXiv | Cycle triplets | ReliableSwap: Boosting General Face Swapping Via Reliable Supervision | Code |
| 2023 | CVPR | Difussion | DiffSwap: High-Fidelity and Controllable Face Swapping via 3D-Aware Masked Diffusion | Code |
| 2023 | arXiv | Difussion | A Generalist FaceX via Learning Unified Facial Representation | Code |
| 2022 | AAAI | GANs | MobileFaceSwap: A Lightweight Framework for Video Face Swapping | Code |
| 2022 | T-PAMI | GANs | FSGANv2: Improved Subject Agnostic Face Swapping and Reenactment | Code |
| 2022 | ICME | GANs | Migrating face swap to mobile devices: a lightweight framework and a supervised training solution | Code |
| 2022 | ECCV | GANs | StyleSwap: Style-Based Generator Empowers Robust Face Swapping | Code |
| 2022 | ECCV | GANs | Designing One Unified Framework for High-Fidelity Face Reenactment and Swapping | Code |
| 2022 | ECCV | GANs+3DMM | MFIM: Megapixel Facial Identity Manipulation | - |
| 2022 | CVPR | GANs | Region-Aware Face Swapping | Code |
| 2022 | CVPR | Difussion | Smooth-Swap: A Simple Enhancement for Face-Swapping with Smoothness | - |
| 2022 | arXiv | Difussion | DiffFace: Diffusion-based Face Swapping with Facial Guidance | Code |
| 2022 | CVPR | GANs | High-resolution Face Swapping via Latent Semantics Disentanglement | Code |
| 2021 | CVPR | GANs+3DMM | FaceInpainter: High Fidelity Face Adaptation to Heterogeneous Domains | - |
| 2021 | CVPR | GANs | Information Bottleneck Disentanglement for Identity Swapping | - |
| 2021 | CVPR | GANs | One Shot Face Swapping on Megapixels | Code |
| 2021 | MMM | GANs | Deep Face Swapping via Cross-Identity Adversarial Training | - |
| 2021 | IJCAI | GANs+3DMM | HifiFace: 3D Shape and Semantic Prior Guided High Fidelity Face Swapping | Code |
| 2020 | CVPR | GANs | FaceShifter: Towards High Fidelity And Occlusion Aware Face Swapping | Code |
| 2020 | CVPR | GANs | DeepFaceLab: Integrated, flexible and extensible face-swapping framework | Code |
| 2020 | NeurIPS | GANs | AOT: Appearance Optimal Transport Based Identity Swapping for Forgery Detection | Code |
| 2020 | ACM MM | GANs+VAEs | SimSwap: An Efficient Framework For High Fidelity Face Swapping | Code |
| 2020 | AAAI | GANs+VAEs | Deepfakes for Medical Video De-Identification: Privacy Protection and Diagnostic Information Preservation | - |
| Year | Venue | Paper Title | Code |
|---|---|---|---|
| 2024 | arXiv | Learning to Generate Conditional Tri-plane for 3D-aware Expression Controllable Portrait Animation | Code |
| 2024 | arXiv | Superior and Pragmatic Talking Face Generation with Teacher-Student Framework | Code |
| 2024 | arXiv | DiffusionAct: Controllable Diffusion Autoencoder for One-shot Face Reenactment | Code |
| 2024 | WACV | CVTHead: One-shot Controllable Head Avatar with Vertex-feature Transformer | Code |
| 2024 | CVPR | FSRT: Facial Scene Representation Transformer for Face Reenactment from Factorized Appearance, Head-pose, and Facial Expression Features | Code |
| 2024 | ICASSP | Expression Domain Translation Network for Cross-Domain Head Reenactment | - |
| 2024 | AAAI | Learning Dense Correspondence for NeRF-Based Face Reenactment | - |
| 2024 | AAAI | FG-EmoTalk: Talking Head Video Generation with Fine-Grained Controllable Facial Expressions | - |
| 2024 | IJCV | One-shot Neural Face Reenactment via Finding Directions in GAN's Latent Space | - |
| 2023 | arXiv | One-Shot Face Video Re-enactment using Hybrid Latent Spaces of StyleGAN2 | Code |
| 2023 | arXiv | MaskRenderer: 3D-Infused Multi-Mask Realistic Face Reenactment | - |
| 2023 | T-PAMI | Free-headgan: Neural talking head synthesis with explicit gaze control | - |
| 2023 | CVPR | High-Fidelity and Freely Controllable Talking Head Video Generation | Code |
| 2023 | NeurIPS | Learning Motion Refinement for Unsupervised Face Animation | Code |
| 2023 | ICCV | ToonTalker: Cross-Domain Face Reenactment | - |
| 2023 | ICCV | HyperReenact: One-Shot Reenactment via Jointly Learning to Refine and Retarget Faces | Code |
| 2023 | CVPR | MetaPortrait: Identity-Preserving Talking Head Generation with Fast Personalized Adaptation | Code |
| 2023 | CVPR | Parametric Implicit Face Representation for Audio-Driven Facial Reenactment | - |
| 2023 | CVPR | One-shot high-fidelity talking-head synthesis with deformable neural radiance field | Code |
| 2023 | FG | Stylemask: Disentangling the style space of stylegan2 for neural face reenactment | Code |
| 2022 | ECCV | Face2Faceρ: Real-Time High-Resolution One-Shot Face Reenactment | - |
| 2022 | CVPR | Dual-Generator Face Reenactment | - |
| 2021 | ICCV | PIRenderer: Controllable Portrait Image Generation via Semantic Neural Rendering | Code |
| 2021 | ICCV | Headgan: One-shot neural head synthesis and editing | - |
| 2020 | CVPR | FReeNet: Multi-Identity Face Reenactment | - |
| 2020 | FG | Head2Head: Videobased neural head synthesis | - |
| 2020 | ECCV | Fast bilayer neural synthesis of one-shot realistic head avatars | - |
| 2020 | AAAI | MarioNETte: Few-Shot Face Reenactment Preserving Identity of Unseen Targets | - |
| 2019 | ACM TOG | Deferred Neural Rendering: Image Synthesis using Neural Textures | - |
| 2019 | ACM TOG | Neural style-preserving visual dubbing | - |
| 2019 | ICCV | Few-Shot Adversarial Learning of Realistic Neural Talking Head Models | - |
| 2018 | CVPR | X2Face: A network for controlling face generation using images, audio, and pose codes | - |
| 2018 | ACM TOG | Deep video portraits | - |
| 2018 | NeurIPS | Video to video synthesis | Code |
| 2016 | CVPR | Face2Face: Real-time Face Capture and Reenactment of RGB Videos | - |
| Year | Venue | Category | Paper Title | Code |
|---|---|---|---|---|
| 2024 | arXiv | 3D Model | GaussianTalker: Real-Time High-Fidelity Talking Head Synthesis with Audio-Driven 3D Gaussian Splatting | Code |
| 2024 | arXiv | 3D Model | Learn2Talk: 3D Talking Face Learns from 2D Talking Face | Code |
| 2024 | arXiv | 3D Model | TalkingGaussian: Structure-Persistent 3D Talking Head Synthesis via Gaussian Splatting | Code |
| 2024 | arXiv | 3D Model | GaussianTalker: Speaker-specific Talking Head Synthesis via 3D Gaussian Splatting | - |
| 2024 | arXiv | Audio | VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Time | Code |
| 2024 | arXiv | Audio | Emote Portrait Alive: Generating Expressive Portrait Videos with Audio2Video Diffusion Model under Weak Conditions | Code |
| 2024 | arXiv | Audio | VLOGGER: Multimodal Diffusion for Embodied Avatar Synthesis | Code |
| 2024 | arXiv | Audio | AniPortrait: Audio-Driven Synthesis of Photorealistic Portrait Animations | Code |
| 2024 | arXiv | Audio | EDTalk: Efficient Disentanglement for Emotional Talking Head Synthesis | Code |
| 2024 | arXiv | Audio | FlowVQTalker: High-Quality Emotional Talking Face Generation through Normalizing Flow and Quantization | - |
| 2024 | arXiv | Audio | Talk3D: High-Fidelity Talking Portrait Synthesis via Personalized 3D Generative Prior | Code |
| 2024 | arXiv | Diffusion | MoDiTalker: Motion-Disentangled Diffusion Model for High-Fidelity Talking Head Generation | - |
| 2024 | arXiv | Audio | EmoVOCA: Speech-Driven Emotional 3D Talking Heads | - |
| 2024 | arXiv | Diffusion | Context-aware Talking Face Video Generation | - |
| 2024 | arXiv | Audio | FaceChain-ImagineID: Freely Crafting High-Fidelity Diverse Talking Faces from Disentangled Audio | Code |
| 2024 | arXiv | Audio | EmoSpeaker: One-shot Fine-grained Emotion-Controlled Talking Face Generation | Code |
| 2024 | arXiv | Audio | ReliTalk: Relightable Talking Portrait Generation from a Single Video | Code |
| 2024 | ICLR | 3D Model | Real3D-Portrait: One-shot Realistic 3D Talking Portrait Synthesis | Code |
| 2024 | T-PAMI | Multimodal | StyleTalk++: A Unified Framework for Controlling the Speaking Styles of Talking Heads | - |
| 2024 | ICASSP | Text | Text-Driven Talking Face Synthesis by Reprogramming Audio-Driven Models | - |
| 2024 | ICASSP | Audio | Speech-Driven Emotional 3d Talking Face Animation Using Emotional Embeddings | - |
| 2024 | ICASSP | Audio | Exploring Phonetic Context-Aware Lip-Sync for Talking Face Generation | - |
| 2024 | ICASSP | Audio | Talking Face Generation for Impression Conversion Considering Speech Semantics | - |
| 2024 | ICASSP | 3D Model | NeRF-AD: Neural Radiance Field with Attention-based Disentanglement for Talking Face Synthesis | Code |
| 2024 | ICASSP | 3D Model | DT-NeRF: Decomposed Triplane-Hash Neural Radiance Fields For High-Fidelity Talking Portrait Synthesis | - |
| 2024 | ICASSP | Multimodal | Talking Face Generation for Impression Conversion Considering Speech Semantics | - |
| 2024 | ICAART | Diffusion | DiT-Head: High-Resolution Talking Head Synthesis using Diffusion Transformers | - |
| 2024 | WACV | Diffusion | Diffused Heads: Diffusion Models Beat GANs on Talking-Face Generation | Code |
| 2024 | WACV | Audio | DR2: Disentangled Recurrent Representation Learning for Data-Efficient Speech Video Synthesis | - |
| 2024 | WACV | Audio | RADIO: Reference-Agnostic Dubbing Video Synthesis | - |
| 2024 | WACV | Audio | Diff2Lip: Audio Conditioned Diffusion Models for Lip-Synchronization | Code |
| 2024 | CVPR | 3D Model | SyncTalk: The Devil is in the Synchronization for Talking Head Synthesis | Code |
| 2024 | CVPR | 3D Model | Learning Dynamic Tetrahedra for High-Quality Talking Head Synthesis | Code |
| 2024 | AAAI | 3D Model | AE-NeRF: Audio Enhanced Neural Radiance Field for Few Shot Talking Head Synthesis | - |
| 2024 | AAAI | 3D Model | Mimic: Speaking Style Disentanglement for Speech-Driven 3D Facial Animation | Code |
| 2024 | AAAI | Audio | Style2Talker: High-Resolution Talking Head Generation with Emotion Style and Art Style | - |
| 2024 | AAAI | Audio | AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head | - |
| 2024 | AAAI | Audio | Say Anything with Any Style | - |
| 2023 | CVPR | Multimodal | High-Fidelity Generalized Emotional Talking Face Generation With Multi-Modal Emotion Space Learning | - |
| 2023 | CVPR | Multimodal | LipFormer: High-fidelity and Generalizable Talking Face Generation with A Pre-learned Facial Codebook | - |
| 2023 | CVPR | Audio | Sadtalker: Learning realistic 3d motion coefficients for stylized audio-driven single image talking face animation | Code |
| 2023 | CVPR | Audio | Seeing What You Said: Talking Face Generation Guided by a Lip Reading Expert | - |
| 2023 | ICCV | Audio | Speech2Lip: High-fidelity Speech to Lip Generation by Learning from a Short Video | Code |
| 2023 | ICCV | Audio | EMMN: Emotional Motion Memory Network for Audio-driven Emotional Talking Face Generation | - |
| 2023 | TNNLS | Audio | Talking Face Generation With Audio-Deduced Emotional Landmarks | - |
| 2023 | ICASSP | Audio | Memory-augmented contrastive learning for talking head generation | Code |
| 2023 | CVPR | Audio | Identity-Preserving Talking Face Generation with Landmark and Appearance Priors | Code |
| 2023 | TCSVT | Audio | Stochastic Latent Talking Face Generation Towards Emotional Expressions and Head Poses | - |
| 2023 | ICCV | Audio | Efficient Emotional Adaptation for Audio-Driven Talking-Head Generation | Code |
| 2023 | arXiv | Audio | GMTalker: Gaussian Mixture based Emotional talking video Portraits | Code |
| 2023 | Displays | Audio | Talking face generation driven by time–frequency domain features of speech audio | - |
| 2023 | arXiv | Diffusion | DreamTalk: When Expressive Talking Head Generation Meets Diffusion Probabilistic Models | Code |
| 2023 | ICCV | Diffusion | Talking Head Generation with Probabilistic Audio-to-Visual Diffusion Priors | Code |
| 2023 | arXiv | Diffusion | DREAM-Talk: Diffusion-based Realistic Emotional Audio-driven Method for Single Image Talking Face Generation | Code |
| 2023 | ICCV | Audio | SPACE : Speech-driven Portrait Animation with Controllable Expression | Code |
| 2023 | Displays | Multimodal | Flow2Flow: Audio-visual cross-modality generation for talking face videos with rhythmic head | Code |
| 2023 | ICCV | 3D Model | EmoTalk: Speech-Driven Emotional Disentanglement for 3D Face Animation | Code |
| 2023 | arXiv | Text | TalkCLIP: Talking Head Generation with Text-Guided Expressive Speaking Styles | - |
| 2023 | ACM MM | Diffusion | DAE-Talker: High Fidelity Speech-Driven Talking Face Generation with Diffusion Autoencoder | Code |
| 2022 | CVPR | Multimodal | Expressive Talking Head Generation with Granular Audio-Visual Control | - |
| 2022 | TMM | Multimodal | Multimodal Learning for Temporally Coherent Talking Face Generation With Articulator Synergy | Code |
| 2022 | CVPR | Text | Talking Face Generation with Multilingual TTS | Code |
| 2022 | ECCV | Audio | Learning Dynamic Facial Radiance Fields for Few-Shot Talking Head Synthesis | Code |
| 2021 | ICCV | Audio | FACIAL: Synthesizing Dynamic Talking Face with Implicit Attribute Learning | Code |
| 2021 | CVPR | Multimodal | Pose-Controllable Talking Face Generation by Implicitly Modularized Audio-Visual Representation | Code |
| 2021 | ICCV | 3D Model | AD-NeRF: Audio Driven Neural Radiance Fields for Talking Head Synthesis | Code |
| 2021 | CVPR | Audio | Audio-driven emotional video portraits | Code |
| 2020 | ICMR | Audio | A Lip Sync Expert Is All You Need for Speech to Lip Generatio In The Wild | Code |
| 2020 | ACM TOG | Audio | MakeItTalk: Speaker-Aware Talking-Head Animation | Code |
| Year | Venue | Category | Paper Title | Code |
|---|---|---|---|---|
| 2024 | arXiv | NeRF | Fast Text-to-3D-Aware Face Generation and Manipulation via Direct Cross-modal Mapping and Geometric Regularization | Code |
| 2024 | arXiv | GANs | GANTASTIC: GAN-based Transfer of Interpretable Directions for Disentangled Image Editing in Text-to-Image Diffusion Models | Code |
| 2024 | arXiv | Diffusion | DreamSalon: A Staged Diffusion Framework for Preserving Identity-Context in Editable Face Generation | - |
| 2024 | arXiv | GANs | S3Editor: A Sparse Semantic-Disentangled Self-Training Framework for Face Video Editing | - |
| 2024 | arXiv | GANs | Reference-Based 3D-Aware Image Editing with Triplane | Code |
| 2024 | arXiv | GANs | 3D-aware Image Generation and Editing with Multi-modal Conditions | - |
| 2024 | arXiv | 3DGS | View-Consistent 3D Editing with Gaussian Splatting | - |
| 2024 | arXiv | GANs | Reference-Based 3D-Aware Image Editing with Triplane | - |
| 2024 | arXiv | GANs | SeFFeC: Semantic Facial Feature Control for Fine-grained Face Editing | - |
| 2024 | arXiv | NeRF | GeneAvatar: Generic Expression-Aware Volumetric Head Avatar Editing from a Single Image | Code |
| 2024 | arXiv | GANs | Skull-to-Face: Anatomy-Guided 3D Facial Reconstruction and Editing | Code |
| 2024 | arXiv | Diffusion | DiffFAE: Advancing High-fidelity One-shot Facial Appearance Editing with Space-sensitive Customization and Semantic Preservation | - |
| 2024 | arXiv | Diffusion | DreamSalon: A Staged Diffusion Framework for Preserving Identity-Context in Editable Face Generation | - |
| 2024 | ICIGP | GANs | A novel method for facial attribute editing by integrating semantic segmentation and color rendering | - |
| 2024 | Information Sciences | GANs | ICGNet: An intensity-controllable generation network based on covering learning for face attribute synthesis | Code |
| 2024 | ICASSP | GANs | Semantic Latent Decomposition with Normalizing Flows for Face Editing | Code |
| 2024 | AAAI | GANs | SDGAN: Disentangling Semantic Manipulation for Facial Attribute Editing | - |
| 2024 | WACV | Diffusion | Personalized Face Inpainting With Diffusion Models by Parallel Visual Attention | - |
| 2024 | NeurIPS | Diffusion+NeRF | FaceDNeRF: Semantics-Driven Face Reconstruction, Prompt Editing and Relighting with Diffusion Models | Code |
| 2023 | CVPR | Diffusion | Collaborative Diffusion for Multi-Modal Face Generation and Editing | Code |
| 2023 | ICCV | GANs | Conceptual and Hierarchical Latent Space Decomposition for Face Editing | - |
| 2023 | NN | GANs | IA-FaceS: A bidirectional method for semantic face editing | Code |
| 2023 | TPAMI | GANs+NeRF | CIPS-3D++: End-to-End Real-Time High-Resolution 3D-Aware GANs for GAN Inversion and Stylization | - |
| 2023 | SIGGRAPH | GANs+3DMM | ClipFace: Text-guided Editing of Textured 3D Morphable Models | Code |
| 2023 | ICCV | GANs | Towards High-Fidelity Text-Guided 3D Face Generation and Manipulation Using only Images | - |
| 2023 | T-PAMI | GANs | Image-to-Image Translation with Disentangled Latent Vectors for Face Editing | Code |
| 2023 | CVPR | GANs | DPE: Disentanglement of Pose and Expression for General Video Portrait Editing | Code |
| 2023 | ACM MM | GANs | PixelFace+: Towards Controllable Face Generation and Manipulation with Text Descriptions and Segmentation Masks | Code |
| 2022 | CVPR | GANs+NeRF | FENeRF: Face Editing in Neural Radiance Fields | Code |
| 2022 | Neural Networks | GANs | GuidedStyle: Attribute Knowledge Guided Style Manipulation for Semantic Face Editing | - |
| 2022 | SIGGRAPH | GANs+NeRF | FDNeRF: Few-shot Dynamic Neural Radiance Fields for Face Reconstruction and Expression Editing | Code |
| 2022 | CVPR | GANs | AnyFace: Free-style Text-to-Face Synthesis and Manipulation | - |
| 2022 | CVPR | GANs | TransEditor: Transformer-Based Dual-Space GAN for Highly Controllable Facial Editing | Code |
| 2022 | SIGGRAPH | GANs+NeRF | NeRFFaceEditing: Disentangled Face Editing in Neural Radiance Fields | - |
| 2022 | TVCG | GANs +3D | Cross-Domain and Disentangled Face Manipulation With 3D Guidance | Code |
| 2021 | ICCV | GANs | A Latent Transformer for Disentangled Face Editing in Images and Videos | Code |
| 2021 | CVPR | GANs | High-Fidelity and Arbitrary Face Editing | Code |
| 2020 | JAS | GANs | MU-GAN: Facial Attribute Editing Based on Multi-Attention Mechanism | Code |
| 2020 | CVPR | GANs | Interpreting the Latent Space of GANs for Semantic Face Editing | Code |
| 2020 | ACCV | GANs | MagGAN: High-Resolution Face Attribute Editing with Mask-Guided Generative Adversarial Network | - |
| Year | Venue | Category | Paper Title | Code |
|---|---|---|---|---|
| 2024 | arXiv | Space Domain | n | - |
| 2024 | arXiv | Multi-Modal | Towards More General Video-based Deepfake Detection through Facial Feature Guided Adaptation for Foundation Model | - |
| 2024 | arXiv | Data Driven | D3: Scaling Up Deepfake Detection by Learning from Discrepancy | - |
| 2024 | arXiv | Space Domain | Band-Attention Modulated RetNet for Face Forgery Detection | - |
| 2024 | arXiv | Other | Real, fake and synthetic faces -- does the coin have three sides? | - |
| 2024 | arXiv | Space Domain | Diffusion Facial Forgery Detection | - |
| 2024 | arXiv | Space Domain | Masked Conditional Diffusion Model for Enhancing Deepfake Detection | - |
| 2024 | T-PAMI | Multi-Modal | Detecting and Grounding Multi-Modal Media Manipulation and Beyond | Code |
| 2024 | ICASSP | Multi-Modal | Exploiting Modality-Specific Features for Multi-Modal Manipulation Detection and Grounding | - |
| 2024 | ICASSP | Space Domain | Selective Domain-Invariant Feature for Generalizable Deepfake Detection | - |
| 2024 | ICASSP | Data Driven | Adapter-Based Incremental Learning for Face Forgery Detection | - |
| 2024 | MMM | Space Domain | Face Forgery Detection via Texture and Saliency Enhancement | - |
| 2024 | MMM | Space Domain | Adapting Pretrained Large-Scale Vision Models for Face Forgery Detection | - |
| 2024 | TIFS | Space Domain | Learning to Discover Forgery Cues for Face Forgery Detection | - |
| 2024 | TIFS | Time Domain | Where Deepfakes Gaze at? Spatial-Temporal Gaze Inconsistency Analysis for Video Face Forgery Detection | Code |
| 2024 | IJCV | Time Domain | Learning Spatiotemporal Inconsistency via Thumbnail Layout for Face Deepfake Detection | Code |
| 2024 | NAACL | Time Domain | Heterogeneity over Homogeneity: Investigating Multilingual Speech Pre-Trained Models for Detecting Audio Deepfake | - |
| 2024 | CVPR | Time Domain | Exploiting Style Latent Flows for Generalizing Deepfake Detection Video Detection | - |
| 2024 | AAAI | Frequency Domain | Frequency-Aware Deepfake Detection: Improving Generalizability through Frequency Space Domain Learning | Code |
| 2024 | AAAI | Space Domain | Exposing the Deception: Uncovering More Forgery Clues for Deepfake Detection | Code |
| 2024 | WACV | Space Domain | Deepfake Detection by Exploiting Surface Anomalies: The SurFake Approach | - |
| 2024 | WACV | Time Domain | VideoFACT: Detecting Video Forgeries Using Attention, Scene Context, and Forensic Traces | Code |
| 2023 | CVPR | Data Driven | Implicit Identity Driven Deepfake Face Swapping Detection | - |
| 2023 | TMM | Data Driven | Narrowing Domain Gaps with Bridging Samples for Generalized Face Forgery Detection | - |
| 2023 | CVPR | Data Driven | Hierarchical Fine-Grained Image Forgery Detection and Localization | Code |
| 2023 | CVPR | Time Domain | Learning on Gradients: Generalized Artifacts Representation for GAN-Generated Images Detection | Code |
| 2023 | ICCV | Data Driven | Towards Generic Image Manipulation Detection with Weakly-Supervised Self-Consistency Learning | - |
| 2023 | ICCV | Data Driven | Quality-Agnostic Deepfake Detection with Intra-model Collaborative Learning | - |
| 2023 | TIFS | Frequency Domain | Constructing New Backbone Networks via Space-Frequency Interactive Convolution for Deepfake Detection | Code |
| 2023 | ICCV | Data Driven | Controllable Guide-Space for Generalizable Face Forgery Detection | - |
| 2023 | AAAI | Space Domain | Noise Based Deepfake Detection via Multi-Head Relative-Interaction | - |
| 2023 | TIFS | Time Domain | Dynamic Difference Learning With Spatio–Temporal Correlation for Deepfake Video Detection | - |
| 2023 | TIFS | Time Domain | Masked Relation Learning for DeepFake Detection | Code |
| 2023 | CVPR | Time Domain | Audio-Visual Person-of-Interest DeepFake Detection | Code |
| 2023 | CVPR | Time Domain | Self-Supervised Video Forensics by Audio-Visual Anomaly Detection | Code |
| 2023 | Applied Soft Computing | Time Domain | AVFakeNet: A unified end-to-end Dense Swin Transformer deep learning model for audio–visual deepfakes detection | - |
| 2023 | TCSVT | Time Domain | PVASS-MDD: Predictive Visual-audio Alignment Self-supervision for Multimodal Deepfake Detection | - |
| 2023 | TIFS | Time Domain | AVoiD-DF: Audio-Visual Joint Learning for Detecting Deepfake | - |
| 2023 | TIFS | Space Domain | Beyond the Prior Forgery Knowledge: Mining Critical Clues for General Face Forgery Detection | Code |
| 2023 | arXiv | Time Domain | AV-Lip-Sync+: Leveraging AV-HuBERT to Exploit Multimodal Inconsistency for Video Deepfake Detection | - |
| 2022 | TIFS | Space Domain | FakeLocator: Robust Localization of GAN-Based Face Manipulations | - |
| 2022 | CVPR | Space Domain | Detecting Deepfakes with Self-Blended Images | Code |
| 2022 | CVPR | Space Domain | End-to-End Reconstruction-Classification Learning for Face Forgery Detection | Code |
| 2022 | ECCV | Space Domain | Explaining Deepfake Detection by Analysing Image Matching | - |
| 2022 | TIFS | Frequency Domain | Hierarchical Frequency-Assisted Interactive Networks for Face Manipulation Detection | - |
| 2022 | ICMR | Time Domain | M2TR: Multi-modal Multi-scale Transformers for Deepfake Detection | Code |
| 2022 | AAAI | Time Domain | Delving into the Local: Dynamic Inconsistency Learning for DeepFake Video Detection | - |
| 2022 | CVPR | Time Domain | Leveraging Real Talking Faces via Self-Supervision for Robust Forgery Detection | Code |
| 2022 | AAAI | Data Driven | FInfer: Frame Inference-Based Deepfake Detection for High-Visual-Quality Videos | - |
| 2021 | CVPR | Space Domain | Multi-attentional Deepfake Detection | Code |
| 2021 | T-PAMI | Space Domain | DeepFake Detection Based on Discrepancies Between Faces and their Context | - |
| 2021 | ICCV | Data Driven | Learning Self-Consistency for Deepfake Detection | - |
| 2021 | CVPR | Frequency Domain | Frequency-aware Discriminative Feature Learning Supervised by Single-Center Loss for Face Forgery Detection | - |
| 2021 | ICCV | Time Domain | Exploring Temporal Coherence for More General Video Face Forgery Detection | Code |
| 2021 | CVPR | Time Domain | Lips Don’t Lie: A Generalisable and Robust Approach to Face Forgery Detection | Code |
| 2021 | CVPR | Time Domain | Detecting Deep-Fake Videos from Aural and Oral Dynamics | - |
| 2020 | IJCAI | Data Driven | FakeSpotter: A Simple yet Robust Baseline for Spotting AI-Synthesized Fake Faces | - |
| 2020 | CVPR | Space Domain | Global Texture Enhancement for Fake Face Detection in the Wild | Code |
| 2020 | CVPR | Data Driven | On the Detection of Digital Face Manipulation | Code |
| 2020 | Signal Processing | Space Domain | Identification of Deep Network Generated Images Using Disparities in Color Components | Code |
| 2020 | CVPR | Space Domain | Face X-ray for More General Face Forgery Detection | - |
| 2020 | ICML | Frequency Domain | Leveraging Frequency Analysis for Deep Fake Image Recognition | Code |
| 2020 | ECCV | Frequency Domain | Thinking in Frequency: Face Forgery Detection by Mining Frequency-aware Clues | - |
| 2020 | ECCV | Frequency Domain | Two-Branch Recurrent Network for Isolating Deepfakes in Videos | - |
| 2020 | ECCV | Space Domain | What makes fake images detectable? Understanding properties that generalize | Code |
| 2019 | ICIP | Space Domain | Detection of Fake Images Via The Ensemble of Deep Representations from Multi Color Spaces | - |
| 2019 | ICIP | Space Domain | Detecting GAN-Generated Imagery Using Saturation Cues | Code |
| 2019 | ICCV | Data Driven | Attributing Fake Images to GANs: Learning and Analyzing GAN Fingerprints | Code |
| 2019 | CVPRW | Space Domain | Exposing DeepFake Videos By Detecting Face Warping Artifacts | Code |
| 2019 | ICASSP | Time Domain | Exposing deep fakes using inconsistent head poses | - |
| 2019 | ICASSP | Space Domain | Capsule-forensics: Using Capsule Networks to Detect Forged Images and Videos | Code |
| 2018 | WIFS | Data Driven | In Ictu Oculi: Exposing AI Generated Fake Face Videos by Detecting Eye Blinking | Code |
| Year | Venue | Paper Title | Code |
|---|---|---|---|
| 2024 | arXiv | Efficient Diffusion Model for Image Restoration by Residual Shifting | Code |
| 2024 | arXiv | PFStorer: Personalized Face Restoration and Super-Resolution | - |
| 2024 | arXiv | DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior | Code |
| 2024 | AAAI | ResDiff: Combining CNN and Diffusion Model for Image Super-Resolution | Code |
| 2024 | AAAI | Low-Light Face Super-resolution via Illumination, Structure, and Texture Associated Representation | Code |
| 2024 | AAAI | SkipDiff: Adaptive Skip Diffusion Model for High-Fidelity Perceptual Image Super-resolution | - |
| 2024 | WACV | Arbitrary-Resolution and Arbitrary-Scale Face Super-Resolution With Implicit Representation Networks | - |
| 2024 | ICASSP | Adaptive Super Resolution for One-Shot Talking-Head Generation | Code |
| 2023 | CVPR | Spatial-Frequency Mutual Learning for Face Super-Resolution | Code |
| 2023 | TIP | CTCNet: A CNN-Transformer Cooperation Network for Face Image Super-Resolution | Code |
| 2023 | TIP | Semi-Cycled Generative Adversarial Networks for Real-World Face Super-Resolution | Code |
| 2023 | TMM | An Efficient Latent Style Guided Transformer-CNN Framework for Face Super-Resolution | Code |
| 2023 | TMM | Exploiting Multi-Scale Parallel Self-Attention and Local Variation via Dual-Branch Transformer-CNN Structure for Face Super-Resolution | - |
| 2023 | NN | Self-attention learning network for face super-resolution | - |
| 2023 | PR | A Composite Network Model for Face Super-Resolution with Multi-Order Head Attention Facial Priors | - |
| 2022 | CVPR | GCFSR: A Generative and Controllable Face Super Resolution Method Without Facial and GAN Priors | Code |
| 2022 | ECCV | From Face to Natural Image: Learning Real Degradation for Blind Image Super-Resolution | Code |
| 2022 | TCSVT | Propagating Facial Prior Knowledge for Multitask Learning in Face Super-Resolution | Code |
| 2022 | NN | Multi-level landmark-guided deep network for face super-resolution | Code |
| Year | Venue | Paper Title | Code |
|---|---|---|---|
| 2024 | arXiv | ToonAging: Face Re-Aging upon Artistic Portrait Style Transfer | - |
| 2024 | arXiv | CtlGAN: Few-shot Artistic Portraits Generation with Contrastive Transfer Learning | - |
| 2024 | Displays | HiStyle: Reinventing historic portraits via 3D generative model | - |
| 2024 | ICASSP | A Framework for Portrait Stylization with Skin-Tone Awareness and Nudity Identification | - |
| 2024 | ICASSP | Learning Discriminative Style Representations for Unsupervised and Few-Shot Artistic Portrait Drawing Generation | Code |
| 2024 | TMM | FaceRefiner: High-Fidelity Facial Texture Refinement with Differentiable Rendering-based Style Transfer | - |
| 2024 | CVPR | Deformable One-shot Face Stylization via DINO Semantic Guidancen | Code |
| 2024 | AAAI | MagiCapture: High-Resolution Multi-Concept Portrait Customization | - |
| 2024 | AAAI | ArtBank: Artistic Style Transfer with Pre-trained Diffusion Model and Implicit Style Prompt Bank | Code |
| 2024 | TNNLS | Few-Shot Face Stylization via GAN Prior Distillation | - |
| 2023 | TNNLS | Unpaired Artistic Portrait Style Transfer via Asymmetric Double-Stream GAN | - |
| 2023 | arXiv | PP-GAN : Style Transfer from Korean Portraits to ID Photos Using Landmark Extractor with GAN | - |
| 2023 | CVPR | Inversion-Based Style Transfer With Diffusion Models | Code |
| 2023 | ICCV | General Image-to-Image Translation with One-Shot Image Guidance | Code |
| 2023 | ACM TOG | A Unified Arbitrary Style Transfer Framework via Adaptive Contrastive Learning | Code |
| 2023 | Neurocomputing | Caster: Cartoon style transfer via dynamic cartoon style casting | - |
| 2023 | IJCV | Learning Portrait Drawing with Unsupervised Parts | - |
| 2022 | CVPR | Pastiche Master: Exemplar-Based High-Resolution Portrait Style Transfer | Code |
| 2022 | ACM TOG | VToonify: Controllable High-Resolution Portrait Video Style Transfer | Code |
| 2022 | ACM TOG | DCT-net: domain-calibrated translation for portrait stylization | Code |
| 2022 | ACM TOG | SofGAN: A Portrait Image Generator with Dynamic Styling | - |
| Year | Venue | Paper Title | Code |
|---|---|---|---|
| 2024 | arXiv | Large Motion Model for Unified Multi-Modal Motion Generation | Code |
| 2024 | arXiv | Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance | Code |
| 2024 | AAAI | PTUS: Photo-Realistic Talking Upper-Body Synthesis via 3D-Aware Motion Decomposition Warping | Code |
| 2024 | CVPR | Emotional Speech-driven 3D Body Animation via Disentangled Latent Diffusion | Code |
| 2024 | CVPR | DISCO: Disentangled Control for Realistic Human Dance Generation | Code |
| 2024 | CVPR | MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model | Code |
| 2024 | CVPR | GaussianAvatar: Towards Realistic Human Avatar Modeling from a Single Video via Animatable 3D Gaussians | Code |
| 2024 | arXiv | Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance | Code |
| 2023 | WACV | Physically Plausible Animation of Human Upper Body From a Single Image | - |
| 2023 | ICCV | Towards Multi-Layered 3D Garments Animation | Code |
| 2023 | ICCV | Make-An-Animation: Large-Scale Text-conditional 3D Human Motion Generation | Code |
| 2023 | CVPR | Learning anchor transformations for 3d garment animation | - |
| 2023 | arXiv | TADA! Text to Animatable Digital Avatars | Code |
| 2022 | IJCAI | Text/Speech-Driven Full-Body Animation | Code |
| 2022 | SIGGRAPH | Capturing and Animation of Body and Clothing from Monocular Video | - |
| 2022 | NeurIPS | CageNeRF: Cage-based Neural Radiance Field for Generalized 3D Deformation and Animation | Code |
| Year | Venue | Paper Title | Code |
|---|---|---|---|
| 2024 | arXiv | Gorgeous: Create Your Desired Character Facial Makeup from Any Ideas | Code |
| 2024 | arXiv | Toward Tiny and High-quality Facial Makeup with Data Amplify Learning | Code |
| 2024 | arXiv | Stable-Makeup: When Real-World Makeup Transfer Meets Diffusion Model | - |
| 2024 | CVPR | Makeup Prior Models for 3D Facial Makeup Estimation and Applications | Code |
| 2024 | ESWA | ISFB-GAN: Interpretable semantic face beautification with generative adversarial network | - |
| 2024 | TVCG | MuNeRF: Robust Makeup Transfer in Neural Radiance Fields | - |
| 2024 | ICASSP | Skin tone disentanglement in 2D makeup transfer with graph neural networks | - |
| 2024 | WACV | LipAT: Beyond Style Transfer for Controllable Neural Simulation of Lipstick Using Cosmetic Attributes | - |
| 2023 | TNNLS | SSAT++: A Semantic-Aware and Versatile Makeup Transfer Network With Local Color Consistency Constraint | Code |
| 2023 | CVPR | BeautyREC: Robust, Efficient, and Component-Specific Makeup Transfer | Code |
| 2023 | TCSVT | Hybrid Transformers with Attention-guided Spatial Embeddings for Makeup Transfer and Removal | - |
| 2023 | arXiv | SARA: Controllable Makeup Transfer with Spatial Alignment and Region-Adaptive Normalization | - |
| 2022 | ICCV | EleGANt: Exquisite and Locally Editable GAN for Makeup Transfer | Code |
| 2022 | AAAI | SSAT: A Symmetric Semantic-Aware Transformer Network for Makeup Transfer and Removal | Code |
| 2022 | Knowledge-Based Systems | TSEV-GAN: Generative Adversarial Networks with Target-aware Style Encoding and Verification for facial makeup transfer | - |
| 2022 | Knowledge-Based Systems | CUMTGAN: An instance-level controllable U-Net GAN for facial makeup transfer | - |
| 2021 | CVPR | Lipstick ain’t enough: beyond color matching for in-the-wild makeup | Code |
| 2021 | T-PAMI | Psgan++: Robust detail-preserving makeup transfer and removal | Code |
| 2020 | CVPR | PSGAN: Pose and Expression Robust Spatial-Aware GAN for Customizable Makeup Transfer | Code |
| 2019 | CVPR | Beautyglow : On-demand makeup transfer framework with reversible generative network | Code |
| 2019 | ICCV | Ladn: Local adversarial disentangling network for facial makeup and de-makeup | Code |
| 2018 | ACM MM | BeautyGAN: Instance-level Facial Makeup Transfer with Deep Generative Adversarial Network | Code |
| 2018 | CVPR | Pairedcyclegan: Asymmetric style transfer for applying and removing makeup | - |
| 2017 | AAAI | Examples-rules guided deep neural network for makeup recommendation | - |
If you find our survey and repository useful for your research project, please consider citing our paper:
@article{pei2024deepfake,
title={Deepfake Generation and Detection: A Benchmark and Survey},
author={Pei, Gan and Zhang, Jiangning and Hu, Menghan and Zhang, Zhenyu and Wang, Chengjie and Wu, Yunsheng and Zhai, Guangtao and Yang, Jian and Shen, Chunhua and Tao, Dacheng},
journal={arXiv preprint arXiv:2403.17881},
year={2024}
}51265904018@stu.ecnu.edu.cn
186368@zju.edu.cn
