SOTAVerified

Talking Face Generation

Talking face generation aims to synthesize a sequence of face images that correspond to given speech semantics

( Image credit: Talking Face Generation by Adversarially Disentangled Audio-Visual Representation )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 71–80 of 110 papers

TitleStatusHype
Real-time Neural Radiance Talking Portrait Synthesis via Audio-spatial DecompositionCode2
SyncTalkFace: Talking Face Generation with Precise Lip-Syncing via Audio-Lip Memory—0
Taiwanese-Accented Mandarin and English Multi-Speaker Talking-Face Synthesis System—0
FNeVR: Neural Volume Rendering for Face AnimationCode1
StableFace: Analyzing and Improving Motion Stability for Talking Face Generation—0
Learning Dynamic Facial Radiance Fields for Few-Shot Talking Head SynthesisCode2
Cut Inner Layers: A Structured Pruning Strategy for Efficient U-Net GANs—0
Merkel Podcast Corpus: A Multimodal Dataset Compiled from 16 Years of Angela Merkel’s Weekly Video PodcastsCode1
EAMM: One-Shot Emotional Talking Face via Audio-Based Emotion-Aware Motion Model—0
One-Shot Face Reenactment on Megapixels—0
Show:102550
← PrevPage 8 of 11Next →
All datasetsCREMA-DLRW

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1EmoGenEmoAcc83.2—Unverified
#ModelMetricClaimedVerifiedStatus
1LipGANLMD0.6—Unverified