SOTAVerified|Agents Browse Leaderboard About

Talking Head Generation

Talking head generation is the task of generating a talking face from a set of images of a person.

( Image credit: Few-Shot Adversarial Learning of Realistic Neural Talking Head Models )

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 11–20 of 119 papers

Title	Date	Tasks	Status	Hype
Efficient Emotional Adaptation for Audio-Driven Talking-Head Generation	Sep 10, 2023	Talking Head Generation	CodeCode Available	2
Implicit Identity Representation Conditioned Memory Compensation Network for Talking Head video Generation	Jul 19, 2023	Talking Head GenerationVideo Generation	CodeCode Available	2
RenderMe-360: A Large Digital Asset Library and Benchmarks Towards High-fidelity Head Avatars	May 22, 2023	2kImage Matting	CodeCode Available	2
DaGAN++: Depth-Aware Generative Adversarial Network for Talking Head Video Generation	May 10, 2023	3D geometryGenerative Adversarial Network	CodeCode Available	2
Emotionally Enhanced Talking Face Generation	Mar 21, 2023	Face GenerationTalking Face Generation	CodeCode Available	2
DiffTalk: Crafting Diffusion Models for Generalized Audio-Driven Portraits Animation	Jan 10, 2023	DenoisingTalking Head Generation	CodeCode Available	2
StyleTalk: One-shot Talking Head Generation with Controllable Speaking Styles	Jan 3, 2023	DecoderFace Generation	CodeCode Available	2
MetaPortrait: Identity-Preserving Talking Head Generation with Fast Personalized Adaptation	Dec 15, 2022	Face SwappingMeta-Learning	CodeCode Available	2
Learning Dynamic Facial Radiance Fields for Few-Shot Talking Head Synthesis	Jul 24, 2022	3D geometryNeRF	CodeCode Available	2
Depth-Aware Generative Adversarial Network for Talking Head Video Generation	Mar 13, 2022	3D geometryGenerative Adversarial Network	CodeCode Available	2

Show:10 25 50

← PrevPage 2 of 12Next →

All datasets VoxCeleb2 - 1-shot learning VoxCeleb1 - 1-shot learning VoxCeleb1 - 32-shot learning VoxCeleb1 - 8-shot learning VoxCeleb2 - 8-shot learning 100 sleep nights of 8 caregivers VoxCeleb2 - 32-shot learning

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	Few-shot Adversarial Model	FID	48.5	—	Unverified
2	CainGAN	FID	35	—	Unverified
3	Fast Bi-layer Avatars (medium size)	CSIM	0.65	—	Unverified
4	First Order Motion Model (medium size)	CSIM	0.64	—	Unverified
5	Few-shot Vid-to-vid (medium size)	CSIM	0.6	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	X2Face	FID	45.8	—	Unverified
2	Few-shot Adversarial Model	FID	43	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	X2Face	FID	56.5	—	Unverified
2	Few-shot Adversarial Model	FID	29.5	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	X2Face	FID	51.5	—	Unverified
2	Few-shot Adversarial Model	FID	38	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Few-shot Adversarial Model	FID	42.2	—	Unverified
2	CainGAN	FID	24.9	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Ashok	10%	12	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Few-shot Adversarial Model	FID	30.6	—	Unverified