SOTAVerified

Talking Face Generation

Talking face generation aims to synthesize a sequence of face images that correspond to given speech semantics

( Image credit: Talking Face Generation by Adversarially Disentangled Audio-Visual Representation )

Papers

Showing 125 of 110 papers

TitleStatusHype
Real3D-Portrait: One-shot Realistic 3D Talking Portrait SynthesisCode5
Deepfake Generation and Detection: A Benchmark and SurveyCode4
GeneFace: Generalized and High-Fidelity Audio-Driven 3D Talking Face SynthesisCode4
JoyGen: Audio-Driven 3D Depth-Aware Talking-Face Video EditingCode3
SyncTalk: The Devil is in the Synchronization for Talking Head SynthesisCode3
DINet: Deformation Inpainting Network for Realistic Face Visually Dubbing on High Resolution VideoCode3
A Lip Sync Expert Is All You Need for Speech to Lip Generation In The WildCode3
HyperLips: Hyper Control Lips with High Resolution Decoder for Talking Face GenerationCode2
Identity-Preserving Talking Face Generation with Landmark and Appearance PriorsCode2
Seeing What You Said: Talking Face Generation Guided by a Lip Reading ExpertCode2
Emotionally Enhanced Talking Face GenerationCode2
DPE: Disentanglement of Pose and Expression for General Video Portrait EditingCode2
StyleTalk: One-shot Talking Head Generation with Controllable Speaking StylesCode2
Real-time Neural Radiance Talking Portrait Synthesis via Audio-spatial DecompositionCode2
Learning Dynamic Facial Radiance Fields for Few-Shot Talking Head SynthesisCode2
StyleHEAT: One-Shot High-Resolution Editable Talking Face Generation via Pre-trained StyleGANCode2
Live Speech Portraits: Real-Time Photorealistic Talking-Head AnimationCode2
MakeItTalk: Speaker-Aware Talking-Head AnimationCode2
Joint Co-Speech Gesture and Expressive Talking Face Generation using Diffusion with AdaptersCode1
KAN-Based Fusion of Dual-Domain for Audio-Driven Facial Landmarks GenerationCode1
Controllable Talking Face Generation by Implicit Facial Keypoints EditingCode1
Neural Text to Articulate Talk: Deep Text to Audiovisual Speech Synthesis achieving both Auditory and Photo-realismCode1
DiffDub: Person-generic Visual Dubbing Using Inpainting Renderer with Diffusion Auto-encoderCode1
HDTR-Net: A Real-Time High-Definition Teeth Restoration Network for Arbitrary Talking Face Generation MethodsCode1
FNeVR: Neural Volume Rendering for Face AnimationCode1
Show:102550
← PrevPage 1 of 5Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1EmoGenEmoAcc83.2Unverified
#ModelMetricClaimedVerifiedStatus
1LipGANLMD0.6Unverified