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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–10 of 110 papers

TitleStatusHype
Real3D-Portrait: One-shot Realistic 3D Talking Portrait SynthesisCode5
GeneFace: Generalized and High-Fidelity Audio-Driven 3D Talking Face SynthesisCode4
Deepfake Generation and Detection: A Benchmark and SurveyCode4
A Lip Sync Expert Is All You Need for Speech to Lip Generation In The WildCode3
JoyGen: Audio-Driven 3D Depth-Aware Talking-Face Video EditingCode3
DINet: Deformation Inpainting Network for Realistic Face Visually Dubbing on High Resolution VideoCode3
SyncTalk: The Devil is in the Synchronization for Talking Head SynthesisCode3
DPE: Disentanglement of Pose and Expression for General Video Portrait EditingCode2
Emotionally Enhanced Talking Face GenerationCode2
HyperLips: Hyper Control Lips with High Resolution Decoder for Talking Face GenerationCode2
Show:102550
← PrevPage 1 of 11Next →
All datasetsCREMA-DLRW

Benchmark Results

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