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
LaDTalk: Latent Denoising for Synthesizing Talking Head Videos with High Frequency Details—0
LaughTalk: Expressive 3D Talking Head Generation with Laughter—0
Learning Frame-Wise Emotion Intensity for Audio-Driven Talking-Head Generation—0
LES-Talker: Fine-Grained Emotion Editing for Talking Head Generation in Linear Emotion Space—0
SPEAK: Speech-Driven Pose and Emotion-Adjustable Talking Head Generation—0
MEDTalk: Multimodal Controlled 3D Facial Animation with Dynamic Emotions by Disentangled Embedding—0
MultiTalk: Enhancing 3D Talking Head Generation Across Languages with Multilingual Video Dataset—0
NeRFFaceSpeech: One-shot Audio-driven 3D Talking Head Synthesis via Generative Prior—0
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
OSM-Net: One-to-Many One-shot Talking Head Generation with Spontaneous Head Motions—0
Perceptually Accurate 3D Talking Head Generation: New Definitions, Speech-Mesh Representation, and Evaluation Metrics—0
PMMTalk: Speech-Driven 3D Facial Animation from Complementary Pseudo Multi-modal Features—0
PoseTalk: Text-and-Audio-based Pose Control and Motion Refinement for One-Shot Talking Head Generation—0
RADIO: Reference-Agnostic Dubbing Video Synthesis—0
Responsive Listening Head Generation: A Benchmark Dataset and Baseline—0
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