Wojciech Zielonka

1

Oct 2026arXiv2026

No Distillation Needed: Single-Pass Real-Time Talking Heads via Acausal Noise Shaping

Audio-driven facial animation underpins real-time avatars, telepresence, and embodied virtual agents. And it must run online: each frame emitted from audio observed up to the current time, at interactive rates. Recent progress is dominated by diffusion models, which need many network evaluations per sample and are therefore a poor fit...

arXiv

@article{han2026nodistillation,
    title     = {No Distillation Needed: Single-Pass Real-Time Talking Heads via Acausal Noise Shaping},
    author    = {Yu Han and Dejan Markovic and Alexander Richard and Wojciech Zielonka and Akshay Venkatesh and Cheng-hsin Wuu and Michael Zollhoefer},
    journal   = {arXiv preprint arXiv:2610.11070},
    year      = {2026},
}

arXiv2026

2

Feb 2026Eurographics2026

How to Build Digital Humans? From Priors to Photorealistic Avatars

A comprehensive state-of-the-art report on building digital humans, covering the full pipeline from 3D morphable models and parametric body priors to photorealistic neural avatars. We survey methods for face, head, and full-body avatar creation, including mesh-based representations, neural radiance fields, and 3D Gaussian splatting. The report provides a structured overview...

Code ... arXiv

@article{zielonka2026star,
    author    = {Zielonka, Wojciech and Kirschstein, Tobias and Bolkart, Timo and Giebenhain, Simon and Sklyarova, Vanessa and Deng, Xiang and Xiang, Donglai and Saito, Shunsuke and Liu, Yebin and Nie{\ss}ner, Matthias and Thies, Justus},
    title     = {How to Build Digital Humans? From Priors to Photorealistic Avatars},
    journal   = {Computer Graphics Forum (Eurographics State-of-the-Art Report)},
    volume    = {45},
    number    = {2},
    year      = {2026},
}

Eurographics2026

3

Feb 2026CVPR2026

PhysHead: Simulation-Ready Gaussian Head Avatars

Realistic digital avatars require expressive and dynamic hair motion; however, most existing head avatar methods assume rigid hair movement. These methods often fail to disentangle hair from the head, representing it as a simple outer shell and failing to capture its natural volumetric behavior. In this paper, we address these...

Code ... arXiv Video

@inproceedings{kabadayi2026physhead,
    title     = {PhysHead: Simulation-Ready Gaussian Head Avatars},
    author    = {Kabadayi, Berna and Sklyarova, Vanessa and Zielonka, Wojciech and Thies, Justus and Pons-Moll, Gerard},
    booktitle = {CVPR},
    year      = {2026},
}

CVPR2026

4

Jan 2025CVPR2025

SynShot: Synthetic Prior for Few-Shot Drivable Head Avatar Inversion

We present SynShot, a novel method for the few-shot inversion of a drivable head avatar based on a synthetic prior. We tackle two major challenges. First, state-of-the-art monocular avatar models struggle to generalize to new views and expressions, lacking a strong prior and often overfitting to a specific viewpoint distribution....

Code ... arXiv Video

@inproceedings{zielonka2025synshot,
    title     = {SynShot: Synthetic Prior for Few-Shot Drivable Head Avatar Inversion},
    author    = {Wojciech Zielonka and Stephan J. Garbin and Alexandros Lattas and George Kopanas and Paulo Gotardo and Thabo Beeler and Justus Thies and Timo Bolkart},
    booktitle = {CVPR},
    month     = {June},
    year      = {2025},
}

CVPR2025

5

Mar 2024CVPR2025

GEM: Gaussian Eigen Models for Human Heads

Current personalized neural head avatars face a trade-off: lightweight models lack detail and realism, while high-quality, animatable avatars require significant computational resources, making them unsuitable for commodity devices. To address this gap, we introduce Gaussian Eigen Models (GEM), which provide high-quality, lightweight, and easily controllable head avatars. GEM utilizes 3D...

Code ... arXiv Video

@inproceedings{zielonka2024gem,
    title     = {GEM: Gaussian Eigen Models for Human Heads},
    author    = {Wojciech Zielonka and Timo Bolkart and Thabo Beeler and Justus Thies},
    booktitle = {CVPR},
    month     = {June},
    year      = {2025},
}

CVPR2025

6

Nov 20233DV2025

D3GA: Drivable 3D Gaussian Avatars

We present Drivable 3D Gaussian Avatars (D3GA), a multi-layered 3D controllable model for human bodies that utilizes 3D Gaussian primitives embedded into tetrahedral cages. The advantage of using cages compared to commonly employed linear blend skinning (LBS) is that primitives like 3D Gaussians are naturally re-oriented and their kernels are...

Code ... arXiv Video

@inproceedings{zielonka25dega,
    title        = {Drivable 3D Gaussian Avatars},
    author       = {Wojciech Zielonka and Timur Bagautdinov and Shunsuke Saito and Michael Zollhöfer and Justus Thies and Javier Romero},
    booktitle    = {3DV},
    month        = {March},
    year         = {2025}
}

3DV2025

7

Nov 20233DV2024

GAN-Avatar: Controllable Personalized GAN-based Human Head Avatar

Digital humans and, especially, 3D facial avatars have raised a lot of attention in the past years, as they are the backbone of several applications like immersive telepresence in AR or VR. Despite the progress, facial avatars reconstructed from commodity hardware are incomplete and miss out on parts of the...

Code ... arXiv Video

@inproceedings{kabadayi24ganavatar,
  title        = {GAN-Avatar: Controllable Personalized GAN-based Human Head Avatar},
  author       = {Kabadayi, Berna and Zielonka, Wojciech and Bhatnagar, Bharat Lal and Pons-Moll, Gerard and Thies, Justus},
  booktitle    = {3DV},
  month        = {March},
  year         = {2024}
}

3DV2024

8

Nov 2022CVPR2023

INSTA: Instant Volumetric Head Avatars

For immersive telepresence in AR or VR, we aim for digital humans (avatars) that mimic the motions and facial expressions of the actual subjects participating in a meeting. Besides the motion, these avatars should reflect the human's shape and appearance. INSTA enables avatar reconstruction within approximately 10 minutes from a...

Code ... arXiv Video

@inproceedings{zielonka2022insta,
    title     = {Instant Volumetric Head Avatars},
    author    = {Wojciech Zielonka and Timo Bolkart and Justus Thies},
    booktitle = {CVPR},
    year      = {2023},
    pages     = {4574-4584},
}

CVPR2023

9

Jul 2022ECCV2022

MICA: Towards Metrical Reconstruction of Human Faces

Face reconstruction and tracking is a building block of numerous applications in AR/VR, human-machine interaction, as well as medical applications. Most of these applications rely on a metrically correct prediction of the shape, especially when the reconstructed subject is put into a metrical context. We present MICA, a metrical face...

Code ... arXiv Video

@inproceedings{zielonka2022mica,
title        = {Towards Metrical Reconstruction of Human Faces},
author       = {Wojciech Zielonka and Timo Bolkart and Justus Thies},
booktitle    = {ECCV},
year         = {2022}
}

ECCV2022

10

Oct 2021