FaceParts: Segmentation and Editing of Gaussian Splatting

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zapała, Tymoteusz, Farganus, Julia, Galus, Dominik, Czachorowski, Mikołaj, Syga, Piotr, Spurek, Przemysław
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910218069213184
author Zapała, Tymoteusz
Farganus, Julia
Galus, Dominik
Czachorowski, Mikołaj
Syga, Piotr
Spurek, Przemysław
author_facet Zapała, Tymoteusz
Farganus, Julia
Galus, Dominik
Czachorowski, Mikołaj
Syga, Piotr
Spurek, Przemysław
contents Facial editing is an important task with applications in entertainment, virtual reality, and digital avatars. Most existing approaches rely on generative models in the 2D image domain, while in 3D the task is typically performed through labor-intensive manual editing. We propose FaceParts, a framework for unsupervised segmentation and editing of Gaussian Splatting avatars. Unlike existing 2D or mesh-assisted methods, our approach operates directly in the Gaussian domain, decomposing avatars into semantically coherent facial parts without supervision. The method integrates feature disentanglement, density-based clustering, and FLAME-anchored part transfer, enabling precise editing and cross-avatar part swapping. Experiments on the NeRSemble dataset with 11 subjects demonstrate robust isolation of features such as beards, eyebrows, eyes and mustaches. Quantitative evaluation confirms that transferred segments adapt to pose and expression, while maintaining identity consistency (ID = 0.943), low Average Expression Distance (AED = 0.021) and low Average Pose Distance (APD = 0.004).
format Preprint
id arxiv_https___arxiv_org_abs_2605_13853
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle FaceParts: Segmentation and Editing of Gaussian Splatting
Zapała, Tymoteusz
Farganus, Julia
Galus, Dominik
Czachorowski, Mikołaj
Syga, Piotr
Spurek, Przemysław
Graphics
Artificial Intelligence
Computer Vision and Pattern Recognition
Facial editing is an important task with applications in entertainment, virtual reality, and digital avatars. Most existing approaches rely on generative models in the 2D image domain, while in 3D the task is typically performed through labor-intensive manual editing. We propose FaceParts, a framework for unsupervised segmentation and editing of Gaussian Splatting avatars. Unlike existing 2D or mesh-assisted methods, our approach operates directly in the Gaussian domain, decomposing avatars into semantically coherent facial parts without supervision. The method integrates feature disentanglement, density-based clustering, and FLAME-anchored part transfer, enabling precise editing and cross-avatar part swapping. Experiments on the NeRSemble dataset with 11 subjects demonstrate robust isolation of features such as beards, eyebrows, eyes and mustaches. Quantitative evaluation confirms that transferred segments adapt to pose and expression, while maintaining identity consistency (ID = 0.943), low Average Expression Distance (AED = 0.021) and low Average Pose Distance (APD = 0.004).
title FaceParts: Segmentation and Editing of Gaussian Splatting
topic Graphics
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.13853