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 91–100 of 110 papers

TitleStatusHype
Parallel and High-Fidelity Text-to-Lip GenerationCode1
Txt2Vid: Ultra-Low Bitrate Compression of Talking-Head Videos via TextCode1
Flow-Guided One-Shot Talking Face Generation With a High-Resolution Audio-Visual DatasetCode1
Text2Video: Text-driven Talking-head Video Synthesis with Personalized Phoneme-Pose DictionaryCode1
3D-TalkEmo: Learning to Synthesize 3D Emotional Talking Head—0
Pose-Controllable Talking Face Generation by Implicitly Modularized Audio-Visual RepresentationCode1
AD-NeRF: Audio Driven Neural Radiance Fields for Talking Head SynthesisCode0
Stochastic Talking Face Generation Using Latent Distribution MatchingCode0
A Lip Sync Expert Is All You Need for Speech to Lip Generation In The WildCode3
Speech Driven Talking Face Generation from a Single Image and an Emotion ConditionCode1
Show:102550
← PrevPage 10 of 11Next →
All datasetsCREMA-DLRW

Benchmark Results

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