arXiv AI
Talking Head Synthesis with Facial Landmark Guidance via 3D Gaussian Splatting
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Computer Vision
Sep 28
EmoZone-Talker: Regional Semantic Control of Audio-Driven 3DGS Talking Heads via Facial Action Units
arXiv:2606.15848v2 Announce Type: replace Abstract: 3D Gaussian Splatting (3DGS) has shown strong potential for high-fidelity talking head synthesis. However, enabling fine-grained, interpretable, an...
arXiv Machine Learning
Jun 30
KM-Speaker: Keypoint-Based Style Control for High-Quality Speech-Driven 3D Facial Animation and Dialogue Localization
arXiv:2606. 28568v1 Announce Type: cross Abstract: Speech-driven 3D facial animation methods face significant challenges in simultaneously achieving high-fidelity motion and precise artistic control at production quality.
arXiv Computer Vision
Sep 4
EmbedTalk: Talking Head Synthesis using Gaussian Embeddings
EmbedTalk introduces per‑Gaussian embeddings to drive speech‑driven facial deformations in real‑time talking head synthesis, replacing traditional tri‑plane encodings. This approach improves rendering quality, lip synchronisation, and motion consistency compared to prior 3D Gaussian Splatting methods while producing more compact models that run at 60+ FPS on a laptop GPU. The technique demonstrates competitive performance against state‑of‑the‑art generative models.
arXiv AI
Aug 7
PD-GS: Phoneme-Driven 3DGS for Audio-Driven Talking Heads
arXiv:2608. 05218v1 Announce Type: new Abstract: 3D Gaussian Splatting (3DGS) enables fast, photorealistic talking-head rendering, yet accurate lip articulation remains elusive: mouth motion is often over-smoothed and may violate hard articulatory constraints such as bilabial closures, producing the notorious ``leaky mouth'' artifact.
Hugging Face Trending Papers
Jul 1
GaussianEmoTalker: Real-Time Emotional Talking Head Synthesis with Audio-Driven and Blendshape-Based 3D Gaussian Splatting
Audio-driven talking head synthesis has achieved impressive progress in lip synchronization and visual quality, yet generating expressive emotional avatars with controllable intensity remains challenging, especially under real-time constraints. In this paper, we present GaussianEmoTalker, an audio-driven framework for real-time emotional talking head synthesis based on 3D Gaussian Splatting.
arXiv Computer Vision
Oct 26
AudioLift: Audio-Driven Single Image to Full-Head Gaussian Avatar via Multi-view Video Generation
arXiv:2610.31747v1 Announce Type: new Abstract: Existing 3D talking avatar methods mainly rely on parametric face models including 3DMM or FLAME, whose compact motion representations limit their abil...