StylizedGS: Controllable Stylization for 3D Gaussian Splatting

计算机科学 人工智能 计算机视觉 计算机图形学(图像) 高斯分布 模式识别(心理学) 物理 量子力学
作者
Dingxi Zhang,Yu-Jie Yuan,Zhuoxun Chen,Fang‐Lue Zhang,Zhenliang He,Shiguang Shan,Lin Gao
出处
期刊:IEEE Transactions on Pattern Analysis and Machine Intelligence [IEEE Computer Society]
卷期号:47 (12): 11961-11973 被引量:14
标识
DOI:10.1109/tpami.2025.3604010
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.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
007完成签到,获得积分10
刚刚
1秒前
wu完成签到,获得积分20
2秒前
2秒前
思源的应助被21采纳,获得10
2秒前
小鱼发布了新的文献求助10
2秒前
adshie发布了新的文献求助30
2秒前
3秒前
4秒前
wu发布了新的文献求助10
4秒前
5秒前
小亮哈哈完成签到,获得积分0
5秒前
在水一方的应助被大橙子采纳,获得10
5秒前
lqllql发布了新的文献求助10
5秒前
wanci的应助被chuanchuan采纳,获得10
5秒前
慕青的应助被小萝卜采纳,获得10
7秒前
Xu完成签到,获得积分10
7秒前
7秒前
8秒前
诸葛明明的应助被九章采纳,获得10
8秒前
852的应助被ronald采纳,获得10
9秒前
9秒前
草际鸣蛰完成签到 ,获得积分10
9秒前
认真浩宇发布了新的文献求助10
9秒前
9秒前
9秒前
超级飞侠发布了新的文献求助10
9秒前
HL发布了新的文献求助10
9秒前
CodeCraft的应助被小鱼采纳,获得10
9秒前
CC完成签到 ,获得积分10
11秒前
cy完成签到,获得积分10
12秒前
12秒前
SPUwangshunfeng完成签到,获得积分10
12秒前
13秒前
zfr发布了新的文献求助10
13秒前
JamesPei的应助被诚心巧凡采纳,获得10
14秒前
niuzyang完成签到,获得积分10
14秒前
15秒前
仁爱诗云发布了新的文献求助10
15秒前
15秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 2000
Handbook of Sport Coaching Research 1000
Orthognathic Surgery - 2 Volume Set 500
高分子基功能界面水蒸发材料与应用研究 500
外场增强的水汽发电研究 500
基于结构调控的功能化水诱导发电材料与器件研究 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8194107
求助须知:如何正确求助?哪些是违规求助? 9580062
关于积分的说明 21869017
捐赠科研通 7793713
什么是DOI,文献DOI怎么找? 3437523
关于科研通互助平台的介绍 2560962
邀请新用户注册赠送积分活动 2484264