SOTAVerified

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 AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 101–119 of 119 papers

TitleStatusHype
NLDF: Neural Light Dynamic Fields for Efficient 3D Talking Head Generation—0
OmniTalker: Real-Time Text-Driven Talking Head Generation with In-Context Audio-Visual Style Replication—0
One-Shot Face Reenactment on Megapixels—0
One-Shot High-Fidelity Talking-Head Synthesis with Deformable Neural Radiance Field—0
OPT: One-shot Pose-Controllable Talking Head Generation—0
UniAvatar: Taming Lifelike Audio-Driven Talking Head Generation with Comprehensive Motion and Lighting Control—0
VectorTalker: SVG Talking Face Generation with Progressive Vectorisation—0
VideoAnydoor: High-fidelity Video Object Insertion with Precise Motion Control—0
VividTalk: One-Shot Audio-Driven Talking Head Generation Based on 3D Hybrid Prior—0
VQTalker: Towards Multilingual Talking Avatars through Facial Motion Tokenization—0
Landmark-guided Diffusion Model for High-fidelity and Temporally Coherent Talking Head Generation—0
Teller: Real-Time Streaming Audio-Driven Portrait Animation with Autoregressive Motion Generation—0
Towards Realistic Visual Dubbing with Heterogeneous Sources—0
ReenactGAN: Learning to Reenact Faces via Boundary TransferCode0
A Comprehensive Multi-scale Approach for Speech and Dynamics Synchrony in Talking Head GenerationCode0
Neural Voice Puppetry: Audio-driven Facial ReenactmentCode0
Text-to-Video: a Two-stage Framework for Zero-shot Identity-agnostic Talking-head GenerationCode0
EMOdiffhead: Continuously Emotional Control in Talking Head Generation via DiffusionCode0
Few-Shot Adversarial Learning of Realistic Neural Talking Head ModelsCode0
Show:102550
← PrevPage 5 of 5Next →
All datasetsVoxCeleb2 - 1-shot learningVoxCeleb1 - 1-shot learningVoxCeleb1 - 32-shot learningVoxCeleb1 - 8-shot learningVoxCeleb2 - 8-shot learning100 sleep nights of 8 caregiversVoxCeleb2 - 32-shot learning

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Few-shot Adversarial ModelFID48.5—Unverified
2CainGANFID35—Unverified
3Fast Bi-layer Avatars (medium size)CSIM0.65—Unverified
4First Order Motion Model (medium size)CSIM0.64—Unverified
5Few-shot Vid-to-vid (medium size)CSIM0.6—Unverified
#ModelMetricClaimedVerifiedStatus
1X2FaceFID45.8—Unverified
2Few-shot Adversarial ModelFID43—Unverified
#ModelMetricClaimedVerifiedStatus
1X2FaceFID56.5—Unverified
2Few-shot Adversarial ModelFID29.5—Unverified
#ModelMetricClaimedVerifiedStatus
1X2FaceFID51.5—Unverified
2Few-shot Adversarial ModelFID38—Unverified
#ModelMetricClaimedVerifiedStatus
1Few-shot Adversarial ModelFID42.2—Unverified
2CainGANFID24.9—Unverified
#ModelMetricClaimedVerifiedStatus
1Ashok10%12—Unverified
#ModelMetricClaimedVerifiedStatus
1Few-shot Adversarial ModelFID30.6—Unverified