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 51–100 of 119 papers

TitleStatusHype
PMMTalk: Speech-Driven 3D Facial Animation from Complementary Pseudo Multi-modal Features—0
VividTalk: One-Shot Audio-Driven Talking Head Generation Based on 3D Hybrid Prior—0
SyncTalk: The Devil is in the Synchronization for Talking Head SynthesisCode3
DiffDub: Person-generic Visual Dubbing Using Inpainting Renderer with Diffusion Auto-encoderCode1
LaughTalk: Expressive 3D Talking Head Generation with Laughter—0
OSM-Net: One-to-Many One-shot Talking Head Generation with Spontaneous Head Motions—0
Efficient Emotional Adaptation for Audio-Driven Talking-Head GenerationCode2
RADIO: Reference-Agnostic Dubbing Video Synthesis—0
From Pixels to Portraits: A Comprehensive Survey of Talking Head Generation Techniques and Applications—0
Text-to-Video: a Two-stage Framework for Zero-shot Identity-agnostic Talking-head GenerationCode0
Implicit Identity Representation Conditioned Memory Compensation Network for Talking Head video GenerationCode2
Hierarchical Semantic Perceptual Listener Head Video Generation: A High-performance Pipeline—0
Interactive Conversational Head Generation—0
A Comprehensive Multi-scale Approach for Speech and Dynamics Synchrony in Talking Head GenerationCode0
Emotional Talking Head Generation based on Memory-Sharing and Attention-Augmented Networks—0
Learning Landmarks Motion from Speech for Speaker-Agnostic 3D Talking Heads GenerationCode1
RenderMe-360: A Large Digital Asset Library and Benchmarks Towards High-fidelity Head AvatarsCode2
DaGAN++: Depth-Aware Generative Adversarial Network for Talking Head Video GenerationCode2
High-Fidelity and Freely Controllable Talking Head Video Generation—0
One-Shot High-Fidelity Talking-Head Synthesis with Deformable Neural Radiance Field—0
Face Animation with an Attribute-Guided Diffusion ModelCode1
TalkCLIP: Talking Head Generation with Text-Guided Expressive Speaking Styles—0
FONT: Flow-guided One-shot Talking Head Generation with Natural Head Motions—0
Emotionally Enhanced Talking Face GenerationCode2
DisCoHead: Audio-and-Video-Driven Talking Head Generation by Disentangled Control of Head Pose and Facial ExpressionsCode1
OPT: One-shot Pose-Controllable Talking Head Generation—0
DiffTalk: Crafting Diffusion Models for Generalized Audio-Driven Portraits AnimationCode2
StyleTalk: One-shot Talking Head Generation with Controllable Speaking StylesCode2
MetaPortrait: Identity-Preserving Talking Head Generation with Fast Personalized AdaptationCode2
Talking Head Generation with Probabilistic Audio-to-Visual Diffusion Priors—0
SadTalker: Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face AnimationCode6
Autoregressive GAN for Semantic Unconditional Head Motion GenerationCode1
Compressing Video Calls using Synthetic Talking Heads—0
AutoLV: Automatic Lecture Video Generator—0
Synthesizing Photorealistic Virtual Humans Through Cross-modal Disentanglement—0
StyleTalker: One-shot Style-based Audio-driven Talking Head Video Generation—0
Learning Dynamic Facial Radiance Fields for Few-Shot Talking Head SynthesisCode2
Perceptual Conversational Head Generation with Regularized Driver and Enhanced RendererCode1
One-Shot Face Reenactment on Megapixels—0
Talking Head Generation Driven by Speech-Related Facial Action Units and Audio- Based on Multimodal Representation Fusion—0
DialogueNeRF: Towards Realistic Avatar Face-to-Face Conversation Video Generation—0
Depth-Aware Generative Adversarial Network for Talking Head Video GenerationCode2
Towards Realistic Visual Dubbing with Heterogeneous Sources—0
DFA-NeRF: Personalized Talking Head Generation via Disentangled Face Attributes Neural Rendering—0
Expressive Talking Head Generation With Granular Audio-Visual Control—0
Responsive Listening Head Generation: A Benchmark Dataset and Baseline—0
AI-generated characters for supporting personalized learning and well-beingCode1
AnimeCeleb: Large-Scale Animation CelebHeads Dataset for Head ReenactmentCode1
Talking Head Generation with Audio and Speech Related Facial Action Units—0
Live Speech Portraits: Real-Time Photorealistic Talking-Head AnimationCode2
Show:102550
← PrevPage 2 of 3Next →
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