Pith. sign in

REVIEW 12 cited by

GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussians

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2312.02069 v2 pith:EAP4A4XH submitted 2023-12-04 cs.CV

Shenhan Qian , Tobias Kirschstein , Liam Schoneveld , Davide Davoli , Simon Giebenhain , Matthias Nie{ss}ner This is my paper · ORCID
classification cs.CV
keywords modelphotorealisticmorphableparametersanimationavataravatarsdriving
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

We introduce GaussianAvatars, a new method to create photorealistic head avatars that are fully controllable in terms of expression, pose, and viewpoint. The core idea is a dynamic 3D representation based on 3D Gaussian splats that are rigged to a parametric morphable face model. This combination facilitates photorealistic rendering while allowing for precise animation control via the underlying parametric model, e.g., through expression transfer from a driving sequence or by manually changing the morphable model parameters. We parameterize each splat by a local coordinate frame of a triangle and optimize for explicit displacement offset to obtain a more accurate geometric representation. During avatar reconstruction, we jointly optimize for the morphable model parameters and Gaussian splat parameters in an end-to-end fashion. We demonstrate the animation capabilities of our photorealistic avatar in several challenging scenarios. For instance, we show reenactments from a driving video, where our method outperforms existing works by a significant margin.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 12 Pith papers

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

  1. EmpaAva: An Open-source Agentic 3D-Avatar Empathetic Live Chatbot

    cs.CL 2026-08 conditional novelty 6.0 of 10

    EmpaAva is an open-source, LLM-orchestrated 3D avatar chatbot that perceives user affect from speech and video, plans empathetic replies, and delivers them with synchronized emotional speech and facial motion.

  2. 3D$^2$-Actor: Learning Pose-Conditioned 3D-Aware Denoiser for Realistic Gaussian Avatar Modeling

    cs.CV 2024-12 conditional novelty 6.0 of 10

    3D2-Actor interleaves pose-conditioned 2D denoising with 3D Gaussian rectification to generate realistic, temporally consistent human avatars from multi-view video.

  3. GAF: Gaussian Avatar Reconstruction from Monocular Videos via Multi-view Diffusion

    cs.CV 2024-12 conditional novelty 6.0 of 10

    A normal-map-conditioned multi-view head diffusion model generates pseudo-ground-truth views that regularize Gaussian avatar optimization, improving reconstruction of unobserved head regions from monocular videos.

  4. GASP: Gaussian Avatars with Synthetic Priors

    cs.CV 2024-12 conditional novelty 6.0 of 10

    GASP trains a Gaussian-avatar prior on synthetic humans, then fits and fine-tunes it to a single photo or monocular video to obtain real-time animatable 360-degree avatars.

  5. QUEEN: QUantized Efficient ENcoding of Dynamic Gaussians for Streaming Free-viewpoint Videos

    cs.CV 2024-12 conditional novelty 6.0 of 10

    QUEEN compresses per-frame Gaussian residuals with learned quantization and gating, reaching about 0.7 MB per frame, under 5 seconds of training, and 350 FPS rendering on dynamic scenes.

  6. GaussianSpeech: Audio-Driven Gaussian Avatars

    cs.CV 2024-11 conditional novelty 6.0 of 10

    A transformer-based sequence model drives a lightweight 3D Gaussian avatar from audio, producing synchronized, photorealistic talking-head animations with a new 16-camera dataset.

  7. ConsistentAvatar: Learning to Diffuse Fully Consistent Talking Head Avatar with Temporal Guidance

    cs.CV 2024-11 conditional novelty 6.0 of 10

    ConsistentAvatar aligns a Fourier high-frequency detail map through a diffusion model and uses it, with normals and emotion text, to condition talking-head avatar generation, reducing temporal and expression inconsistency.

  8. S-Avatar: Diffusion-Guided Gaussian Head Avatars from a Single Image

    cs.CV 2026-07 conditional novelty 5.0 of 10

    A three-stage pipeline generates animatable 3D Gaussian head avatars from one image by diffusion-based splat synthesis, FLAME fitting, and inverse-distance binding with scale adaptation.

  9. HairGS: Hair Strand Reconstruction based on 3D Gaussian Splatting

    cs.CV 2025-09 conditional novelty 5.0 of 10

    HairGS reconstructs 3D hair strands from multi-view images in about one hour by fitting 3D Gaussians, merging them into strands with distance and direction rules, and refining them against the photos.

  10. SignSplat: Rendering Sign Language via Gaussian Splatting

    cs.CV 2025-05 conditional novelty 5.0 of 10

    SignSplat renders photo-realistic sign language by anchoring Gaussian splats to an SMPL-X body mesh with regularized optimization and adaptive densification, claiming state-of-the-art results on NeuMan, X-Humans, and ...

  11. Interactive Holographic Visualization for 3D Facial Avatar

    cs.GR 2025-02 reject novelty 5.0 of 10

    A proof-of-concept pipeline that generates real-time 3D facial expressions using a Transformer-based predictor and renders them on a light-field display via 3D Gaussian Splatting, intended for pain-assessment training.

  12. GaussianAvatar-Editor: Photorealistic Animatable Gaussian Head Avatar Editor

    cs.CV 2025-01 conditional novelty 5.0 of 10

    GaussianAvatar-Editor adds a visibility-weighted alpha blending term and a temporal adversarial loss to make text-driven edits of animatable Gaussian head avatars robust to motion occlusion and 4D inconsistency.

Pith tools