paper-with-me

홈 › Papers

Pix2NPHM: Learning to Regress NPHM Reconstructions From a Single Image

2025-12-19 · Simon Giebenhain, Tobias Kirschstein, Liam Schoneveld, Davide Davoli, Zhe Chen, Matthias Nießner arxiv

Neural Parametric Head Models (NPHMs) are a recent advancement over mesh-based 3d morphable models (3DMMs) to facilitate high-fidelity geometric detail. However, fitting NPHMs to visual inputs is notoriously challenging due to the expressive nature of their underlying latent space. To this end, we propose Pix2NPHM, a vision transformer (ViT) network that directly regresses NPHM parameters, given a single image as input. Compared to existing approaches, the neural parametric space allows our method to reconstruct more recognizable facial geometry and accurate facial expressions. For broad generalization, we exploit domain-specific ViTs as backbones, which are pretrained on geometric prediction tasks. We train Pix2NPHM on a mixture of 3D data, including a total of over 100K NPHM registrations that enable direct supervision in SDF space, and large-scale 2D video datasets, for which normal estimates serve as pseudo ground truth geometry. Pix2NPHM not only allows for 3D reconstructions at interactive frame rates, it is also possible to improve geometric fidelity by a subsequent inference-time optimization against estimated surface normals and canonical point maps. As a result, we achieve unprecedented face reconstruction quality that can run at scale on in-the-wild data.

📄 PDF Abstract BibTeX arXiv:2512.17773

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

MonoNPHM: Dynamic Head Reconstruction from Monocular Videos

2023-12-11 · CVPR 2024 1 · Simon Giebenhain, Tobias Kirschstein, Markos Georgopoulos, Martin Rünz 외

We present Monocular Neural Parametric Head Models (MonoNPHM) for dynamic 3D head reconstructions from monocular RGB videos. To this end, we propose a latent appearance space that parameterizes a texture field on top of …

Face ReconstructionInverse Rendering

DiffusionAvatars: Deferred Diffusion for High-fidelity 3D Head Avatars

2023-11-30 · CVPR 2024 1 · Tobias Kirschstein, Simon Giebenhain, Matthias Nießner

DiffusionAvatars synthesizes a high-fidelity 3D head avatar of a person, offering intuitive control over both pose and expression. We propose a diffusion-based neural renderer that leverages generic 2D priors to produce …

FaceTalk: Audio-Driven Motion Diffusion for Neural Parametric Head Models

2023-12-13 · CVPR 2024 1 · Shivangi Aneja, Justus Thies, Angela Dai, Matthias Nießner

We introduce FaceTalk, a novel generative approach designed for synthesizing high-fidelity 3D motion sequences of talking human heads from input audio signal. To capture the expressive, detailed nature of human heads, in…

3D Face AnimationAudio SynthesisMotion Synthesis

NPGA: Neural Parametric Gaussian Avatars

2024-05-29 · Simon Giebenhain, Tobias Kirschstein, Martin Rünz, Lourdes Agapito 외

The creation of high-fidelity, digital versions of human heads is an important stepping stone in the process of further integrating virtual components into our everyday lives. Constructing such avatars is a challenging r…

DPHMs: Diffusion Parametric Head Models for Depth-based Tracking

2023-12-02 · CVPR 2024 1 · Jiapeng Tang, Angela Dai, Yinyu Nie, Lev Markhasin 외

We introduce Diffusion Parametric Head Models (DPHMs), a generative model that enables robust volumetric head reconstruction and tracking from monocular depth sequences. While recent volumetric head models, such as NPHMs…