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 1–10 of 119 papers

TitleStatusHype
MEDTalk: Multimodal Controlled 3D Facial Animation with Dynamic Emotions by Disentangled Embedding—0
Advancing Talking Head Generation: A Comprehensive Survey of Multi-Modal Methodologies, Datasets, Evaluation Metrics, and Loss FunctionsCode1
Silence is Golden: Leveraging Adversarial Examples to Nullify Audio Control in LDM-based Talking-Head GenerationCode1
DualTalk: Dual-Speaker Interaction for 3D Talking Head Conversations—0
KeySync: A Robust Approach for Leakage-free Lip Synchronization in High Resolution—0
OmniTalker: Real-Time Text-Driven Talking Head Generation with In-Context Audio-Visual Style Replication—0
Audio-visual Controlled Video Diffusion with Masked Selective State Spaces Modeling for Natural Talking Head GenerationCode3
Audio-Plane: Audio Factorization Plane Gaussian Splatting for Real-Time Talking Head Synthesis—0
Dual Audio-Centric Modality Coupling for Talking Head Generation—0
Perceptually Accurate 3D Talking Head Generation: New Definitions, Speech-Mesh Representation, and Evaluation Metrics—0
Show:102550
← PrevPage 1 of 12Next →
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
1X2FaceFID51.5—Unverified
2Few-shot Adversarial ModelFID38—Unverified