SOTAVerified

Face Generation

Face generation is the task of generating (or interpolating) new faces from an existing dataset.

The state-of-the-art results for this task are located in the Image Generation parent.

( Image credit: Progressive Growing of GANs for Improved Quality, Stability, and Variation )

Papers

Showing 150 of 381 papers

TitleStatusHype
Real3D-Portrait: One-shot Realistic 3D Talking Portrait SynthesisCode5
GeneFace: Generalized and High-Fidelity Audio-Driven 3D Talking Face SynthesisCode4
Arc2Face: A Foundation Model for ID-Consistent Human FacesCode4
Deepfake Generation and Detection: A Benchmark and SurveyCode4
DeepFakes and Beyond: A Survey of Face Manipulation and Fake DetectionCode4
JoyGen: Audio-Driven 3D Depth-Aware Talking-Face Video EditingCode3
InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANsCode2
FaceScore: Benchmarking and Enhancing Face Quality in Human GenerationCode2
DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face SynthesisCode2
StyleTalk: One-shot Talking Head Generation with Controllable Speaking StylesCode2
Collaborative Diffusion for Multi-Modal Face Generation and EditingCode2
Identity-Preserving Talking Face Generation with Landmark and Appearance PriorsCode2
3DFaceShop: Explicitly Controllable 3D-Aware Portrait GenerationCode2
Seeing What You Said: Talking Face Generation Guided by a Lip Reading ExpertCode2
Interpreting the Latent Space of GANs for Semantic Face EditingCode2
Few-shot Knowledge Transfer for Fine-grained Cartoon Face GenerationCode2
DPE: Disentanglement of Pose and Expression for General Video Portrait EditingCode2
Learning a model of facial shape and expression from 4D scansCode2
Towards Localized Fine-Grained Control for Facial Expression GenerationCode2
CelebV-HQ: A Large-Scale Video Facial Attributes DatasetCode2
Emotionally Enhanced Talking Face GenerationCode2
HyperLips: Hyper Control Lips with High Resolution Decoder for Talking Face GenerationCode2
StyleHEAT: One-Shot High-Resolution Editable Talking Face Generation via Pre-trained StyleGANCode2
Progressive Growing of GANs for Improved Quality, Stability, and VariationCode2
HDTR-Net: A Real-Time High-Definition Teeth Restoration Network for Arbitrary Talking Face Generation MethodsCode1
GANimation: Anatomically-aware Facial Animation from a Single ImageCode1
A Large-scale Universal Evaluation Benchmark For Face Forgery DetectionCode1
High-Fidelity 3D Face Generation from Natural Language DescriptionsCode1
Graph-based Generative Face Anonymisation with Pose PreservationCode1
Grasping the Arrow of Time from the Singularity: Decoding Micromotion in Low-dimensional Latent Spaces from StyleGANCode1
Flow-Guided One-Shot Talking Face Generation With a High-Resolution Audio-Visual DatasetCode1
Fine-Tuning StyleGAN2 For Cartoon Face GenerationCode1
FLUXSynID: A Framework for Identity-Controlled Synthetic Face Generation with Document and Live ImagesCode1
FFaceNeRF: Few-shot Face Editing in Neural Radiance FieldsCode1
ArtNeRF: A Stylized Neural Field for 3D-Aware Cartoonized Face SynthesisCode1
GANalyzer: Analysis and Manipulation of GANs Latent Space for Controllable Face SynthesisCode1
Parallel and High-Fidelity Text-to-Lip GenerationCode1
FACIAL: Synthesizing Dynamic Talking Face with Implicit Attribute LearningCode1
Face Forgery Detection with Elaborate BackboneCode1
Fast Text-to-3D-Aware Face Generation and Manipulation via Direct Cross-modal Mapping and Geometric RegularizationCode1
Encoding in Style: a StyleGAN Encoder for Image-to-Image TranslationCode1
DynaST: Dynamic Sparse Transformer for Exemplar-Guided Image GenerationCode1
BlendGAN: Implicitly GAN Blending for Arbitrary Stylized Face GenerationCode1
ArcFace: Additive Angular Margin Loss for Deep Face RecognitionCode1
A recurrent cycle consistency loss for progressive face-to-face synthesisCode1
Face Reconstruction with Variational Autoencoder and Face MasksCode1
How to Synthesize a Large-Scale and Trainable Micro-Expression Dataset?Code1
EigenGAN: Layer-Wise Eigen-Learning for GANsCode1
Complete Face Recovery GAN: Unsupervised Joint Face Rotation and De-Occlusion From a Single-View ImageCode1
Feature Quantization Improves GAN TrainingCode1
Show:102550
← PrevPage 1 of 8Next →

No leaderboard results yet.