GSwap: Realistic Head Swapping with Dynamic Neural Gaussian Field

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhou, Jingtao, Gao, Xuan, Liu, Dongyu, Hou, Junhui, Guo, Yudong, Zhang, Juyong
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918406604718080
author Zhou, Jingtao
Gao, Xuan
Liu, Dongyu
Hou, Junhui
Guo, Yudong
Zhang, Juyong
author_facet Zhou, Jingtao
Gao, Xuan
Liu, Dongyu
Hou, Junhui
Guo, Yudong
Zhang, Juyong
contents We present GSwap, a novel consistent and realistic video head-swapping system empowered by dynamic neural Gaussian portrait priors, which significantly advances the state of the art in face and head replacement. Unlike previous methods that rely primarily on 2D generative models or 3D Morphable Face Models (3DMM), our approach overcomes their inherent limitations, including poor 3D consistency, unnatural facial expressions, and restricted synthesis quality. Moreover, existing techniques struggle with full head-swapping tasks due to insufficient holistic head modeling and ineffective background blending, often resulting in visible artifacts and misalignments. To address these challenges, GSwap introduces an intrinsic 3D Gaussian feature field embedded within a full-body SMPL-X surface, effectively elevating 2D portrait videos into a dynamic neural Gaussian field. This innovation ensures high-fidelity, 3D-consistent portrait rendering while preserving natural head-torso relationships and seamless motion dynamics. To facilitate training, we adapt a pretrained 2D portrait generative model to the source head domain using only a few reference images, enabling efficient domain adaptation. Furthermore, we propose a neural re-rendering strategy that harmoniously integrates the synthesized foreground with the original background, eliminating blending artifacts and enhancing realism. Extensive experiments demonstrate that GSwap surpasses existing methods in multiple aspects, including visual quality, temporal coherence, identity preservation, and 3D consistency.
format Preprint
id arxiv_https___arxiv_org_abs_2603_23168
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle GSwap: Realistic Head Swapping with Dynamic Neural Gaussian Field
Zhou, Jingtao
Gao, Xuan
Liu, Dongyu
Hou, Junhui
Guo, Yudong
Zhang, Juyong
Computer Vision and Pattern Recognition
We present GSwap, a novel consistent and realistic video head-swapping system empowered by dynamic neural Gaussian portrait priors, which significantly advances the state of the art in face and head replacement. Unlike previous methods that rely primarily on 2D generative models or 3D Morphable Face Models (3DMM), our approach overcomes their inherent limitations, including poor 3D consistency, unnatural facial expressions, and restricted synthesis quality. Moreover, existing techniques struggle with full head-swapping tasks due to insufficient holistic head modeling and ineffective background blending, often resulting in visible artifacts and misalignments. To address these challenges, GSwap introduces an intrinsic 3D Gaussian feature field embedded within a full-body SMPL-X surface, effectively elevating 2D portrait videos into a dynamic neural Gaussian field. This innovation ensures high-fidelity, 3D-consistent portrait rendering while preserving natural head-torso relationships and seamless motion dynamics. To facilitate training, we adapt a pretrained 2D portrait generative model to the source head domain using only a few reference images, enabling efficient domain adaptation. Furthermore, we propose a neural re-rendering strategy that harmoniously integrates the synthesized foreground with the original background, eliminating blending artifacts and enhancing realism. Extensive experiments demonstrate that GSwap surpasses existing methods in multiple aspects, including visual quality, temporal coherence, identity preservation, and 3D consistency.
title GSwap: Realistic Head Swapping with Dynamic Neural Gaussian Field
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.23168