paper-with-me

홈 › Papers

Large-Scale High-Quality 3D Gaussian Head Reconstruction from Multi-View Captures

2026-05-05 · Evangelos Ntavelis, Sean Wu, Mohamad Shahbazi, Fabio Maninchedda, Dmitry Kostiaev, Artem Sevastopolsky, Vittorio Megaro, Trevor Phillips, Alejandro Blumentals, Shridhar Ravikumar, Mehak Gupta, Reinhard Knothe, Jeronimo Bayer, Matthias Vestner, Simon Schaefer, Thomas Etterlin, Christian Zimmermann, Alexey Artemov, Mathias Deschler, Peter Kaufmann, Stefan Brugger, Sebastian Martin, Brian Amberg, Tom Runia arxiv

We propose HeadsUp, a scalable feed-forward method for reconstructing high-quality 3D Gaussian heads from large-scale multi-camera setups. Our method employs an efficient encoder-decoder architecture that compresses input views into a compact latent representation. This latent representation is then decoded into a set of UV-parameterized 3D Gaussians anchored to a neutral head template. This UV representation decouples the number of 3D Gaussians from the number and resolution of input images, enabling training with many high-resolution input views. We train and evaluate our model on an internal dataset with more than 10,000 subjects, which is an order of magnitude larger than existing multi-view human head datasets. HeadsUp achieves state-of-the-art reconstruction quality and generalizes to novel identities without test-time optimization. We extensively analyze the scaling behavior of our model across identities, views, and model capacity, revealing practical insights for quality-compute trade-offs. Finally, we highlight the strength of our latent space by showcasing two downstream applications: generating novel 3D identities and animating the 3D heads with expression blendshapes.

📄 PDF Abstract BibTeX arXiv:2605.04035

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

GGHead: Fast and Generalizable 3D Gaussian Heads

2024-06-13 · Tobias Kirschstein, Simon Giebenhain, Jiapeng Tang, Markos Georgopoulos 외

Learning 3D head priors from large 2D image collections is an important step towards high-quality 3D-aware human modeling. A core requirement is an efficient architecture that scales well to large-scale datasets and larg…

Gaussian Eigen Models for Human Heads

2024-07-05 · CVPR 2025 1 · Wojciech Zielonka, Timo Bolkart, Thabo Beeler, Justus Thies

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 commod…

Duplex-GS: Proxy-Guided Weighted Blending for Real-Time Order-Independent Gaussian Splatting

2025-08-05 · Weihang Liu, Yuke Li, Yuxuan Li, Jingyi Yu 외 arxiv

Recent advances in 3D Gaussian Splatting (3DGS) have demonstrated remarkable rendering fidelity and efficiency. However, these methods still rely on computationally expensive sequential alpha-blending operations, resulti…

GaussianSpeech: Audio-Driven Gaussian Avatars

2024-11-27 · Shivangi Aneja, Artem Sevastopolsky, Tobias Kirschstein, Justus Thies 외

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 hum…

3DGS

HeadGAP: Few-Shot 3D Head Avatar via Generalizable Gaussian Priors

2024-08-12 · Xiaozheng Zheng, Chao Wen, Zhaohu Li, Weiyi Zhang 외

In this paper, we present a novel 3D head avatar creation approach capable of generalizing from few-shot in-the-wild data with high-fidelity and animatable robustness. Given the underconstrained nature of this problem, i…

Decoder