StylizedGS: Controllable Stylization for 3D Gaussian Splatting

doi:10.1109/TPAMI.2025.3604010

CSpace

	StylizedGS: Controllable Stylization for 3D Gaussian Splatting
	Zhang, Dingxi 1,2; Yuan, Yu-Jie 1,2; Chen, Zhuoxun 1,2; Zhang, Fang-Lue 3; He, Zhenliang 2,4; Shan, Shiguang 2,4; Gao, Lin 1,2
	2025-12-01
发表期刊	IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
ISSN	0162-8828
卷号	47 期号:12 页码:11961-11973
摘要	As XR technology continues to advance rapidly, 3D generation and editing are increasingly crucial. Among these, stylization plays a key role in enhancing the appearance of 3D models. By utilizing stylization, users can achieve consistent artistic effects in 3D editing using a single reference style image, making it a user-friendly editing method. However, recent NeRF-based 3D stylization methods encounter efficiency issues that impact the user experience, and their implicit nature limits their ability to accurately transfer geometric pattern styles. Additionally, the ability for artists to apply flexible control over stylized scenes is considered highly desirable to foster an environment conducive to creative exploration. To address the above issues, we introduce StylizedGS, an efficient 3D neural style transfer framework with adaptable control over perceptual factors based on 3D Gaussian Splatting representation. We propose a filter-based refinement to eliminate floaters that affect the stylization effects in the scene reconstruction process. The nearest neighbor-based style loss is introduced to achieve stylization by fine-tuning the geometry and color parameters of 3DGS, while a depth preservation loss with other regularizations is proposed to prevent the tampering of geometry content. Moreover, facilitated by specially designed losses, StylizedGS enables users to control color, stylized scale, and regions during the stylization to possess customization capabilities. Our method achieves high-quality stylization results characterized by faithful brushstrokes and geometric consistency with flexible controls. Extensive experiments across various scenes and styles demonstrate the effectiveness and efficiency of our method concerning both stylization quality and inference speed.
关键词	Three-dimensional displays Image color analysis Rendering (computer graphics) Geometry Image reconstruction Training Optimization Semantics Neural radiance field Visualization Gaussian splatting style transfer perceptual control
DOI	10.1109/TPAMI.2025.3604010
收录类别	SCI
语种	英语
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:001609560700008
出版者	IEEE COMPUTER SOC
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/42898
专题	中国科学院计算技术研究所
通讯作者	Gao, Lin
作者单位	1.Chinese Acad Sci, Beijing Key Lab Mobile Comp & Pervas Device, Inst Comp Technol, Beijing 100045, Peoples R China 2.Univ Chinese Acad Sci, Beijing 101408, Peoples R China 3.Victoria Univ Wellington, Wellington 6140, New Zealand 4.Chinese Acad Sci, Key Lab Intelligent Informat Proc, Inst Comp Technol, Beijing 100045, Peoples R China
推荐引用方式 GB/T 7714	Zhang, Dingxi,Yuan, Yu-Jie,Chen, Zhuoxun,et al. StylizedGS: Controllable Stylization for 3D Gaussian Splatting[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2025,47(12):11961-11973.
APA	Zhang, Dingxi.,Yuan, Yu-Jie.,Chen, Zhuoxun.,Zhang, Fang-Lue.,He, Zhenliang.,...&Gao, Lin.(2025).StylizedGS: Controllable Stylization for 3D Gaussian Splatting.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,47(12),11961-11973.
MLA	Zhang, Dingxi,et al."StylizedGS: Controllable Stylization for 3D Gaussian Splatting".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 47.12(2025):11961-11973.