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 61–70 of 110 papers

TitleStatusHype
DINet: Deformation Inpainting Network for Realistic Face Visually Dubbing on High Resolution VideoCode3
UniFLG: Unified Facial Landmark Generator from Text or Speech—0
GeneFace: Generalized and High-Fidelity Audio-Driven 3D Talking Face SynthesisCode4
DPE: Disentanglement of Pose and Expression for General Video Portrait EditingCode2
Diffused Heads: Diffusion Models Beat GANs on Talking-Face Generation—0
StyleTalk: One-shot Talking Head Generation with Controllable Speaking StylesCode2
EMMN: Emotional Motion Memory Network for Audio-driven Emotional Talking Face Generation—0
LipFormer: High-Fidelity and Generalizable Talking Face Generation With a Pre-Learned Facial Codebook—0
Emotional Talking Faces: Making Videos More Expressive and Realistic—0
Memories are One-to-Many Mapping Alleviators in Talking Face Generation—0
Show:102550
← PrevPage 7 of 11Next →
All datasetsCREMA-DLRW

Benchmark Results

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