Pith. sign in

REVIEW 4 cited by

GaussianSpeech: Audio-Driven Gaussian Avatars

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2411.18675 v1 pith:CHNKGJ4L submitted 2024-11-27 cs.CV cs.AIcs.GRcs.SDeess.AS

classification cs.CVcs.AIcs.GRcs.SDeess.AS
keywords audiofacialgaussiangaussianspeechsequencesavatarsdiverseexpressions
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We introduce GaussianSpeech, a novel approach that synthesizes high-fidelity animation sequences of photo-realistic, personalized 3D human head avatars from spoken audio. To capture the expressive, detailed nature of human heads, including skin furrowing and finer-scale facial movements, we propose to couple speech signal with 3D Gaussian splatting to create realistic, temporally coherent motion sequences. We propose a compact and efficient 3DGS-based avatar representation that generates expression-dependent color and leverages wrinkle- and perceptually-based losses to synthesize facial details, including wrinkles that occur with different expressions. To enable sequence modeling of 3D Gaussian splats with audio, we devise an audio-conditioned transformer model capable of extracting lip and expression features directly from audio input. Due to the absence of high-quality datasets of talking humans in correspondence with audio, we captured a new large-scale multi-view dataset of audio-visual sequences of talking humans with native English accents and diverse facial geometry. GaussianSpeech consistently achieves state-of-the-art performance with visually natural motion at real time rendering rates, while encompassing diverse facial expressions and styles.

Discussion (0). Sign in to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. FFAvatar: Feed-Forward 4D Head Avatar Reconstruction from Sparse Portrait Images

    cs.CV 2026-06 unverdicted novelty 6.0 of 10

    FFAvatar uses a Transformer-based 3D Gaussian model with alternating attention and sparse-to-dense learning to enable feed-forward, incremental reconstruction of animatable 4D head avatars from sparse portrait images.

  2. MoGaFace: Momentum-Guided and Texture-Aware Gaussian Avatars for Consistent Facial Geometry

    cs.CV 2025-08 unverdicted novelty 6.0 of 10

    MoGaFace improves 3D head avatar rendering by combining momentum-based expression correction with latent texture attention in Gaussian splatting, boosting novel-view quality under imperfect mesh tracking.

  3. Few-Shot Identity Adaptation for 3D Talking Heads via Global Gaussian Field

    cs.CV 2025-06 conditional novelty 5.0 of 10

    A shared global Gaussian field plus identity embeddings lets a 3D talking head model adapt to new speakers with a few seconds of footage while improving quality over prior per-identity models.

  4. GGTalker: Talking Head Systhesis with Generalizable Gaussian Priors and Identity-Specific Adaptation

    cs.CV 2025-06 conditional novelty 5.0 of 10

    GGTalker combines large-scale audio-to-expression and expression-to-texture priors with rapid per-identity fine-tuning to create high-quality 3D talking heads from a short video.

Pith tools