SOTAVerified|Agents Browse Leaderboard About

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 Added Most Hyped Most Active Needs Verification Most Verified

Showing 101–110 of 110 papers

Title	Date	Tasks	Status	Hype
MEAD: A Large-scale Audio-visual Dataset for Emotional Talking-face Generation	Aug 1, 2020	Face GenerationTalking Face Generation	CodeCode Available	1
Identity-Preserving Realistic Talking Face Generation	May 25, 2020	Audio-Visual SynchronizationFace Generation	—Unverified	0
MakeItTalk: Speaker-Aware Talking-Head Animation	Apr 27, 2020	Talking Face GenerationTalking Head Generation	CodeCode Available	2
Neural Voice Puppetry: Audio-driven Facial Reenactment	Dec 11, 2019	Face ModelNeural Rendering	CodeCode Available	0
Hierarchical Cross-Modal Talking Face Generation With Dynamic Pixel-Wise Loss	Jun 1, 2019	Face GenerationTalking Face Generation	—Unverified	0
Capture, Learning, and Synthesis of 3D Speaking Styles	May 8, 2019	3D Face AnimationTalking Face Generation	CodeCode Available	0
Arbitrary Talking Face Generation via Attentional Audio-Visual Coherence Learning	Dec 17, 2018	Face GenerationTalking Face Generation	—Unverified	0
ReenactGAN: Learning to Reenact Faces via Boundary Transfer	Jul 29, 2018	DecoderFace Reenactment	CodeCode Available	0
Talking Face Generation by Adversarially Disentangled Audio-Visual Representation	Jul 20, 2018	Face GenerationLip Reading	CodeCode Available	0
Talking Face Generation by Conditional Recurrent Adversarial Network	Apr 13, 2018	Constrained Lip-synchronizationFace Generation	CodeCode Available	0

Show:10 25 50

← PrevPage 5 of 5Next →

All datasets CREMA-D LRW

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	EmoGen	EmoAcc	83.2	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	LipGAN	LMD	0.6	—	Unverified