Mip-Splatting: Alias-Free 3D Gaussian Splatting
2024
会议录名称PROCEEDINGS OF THE IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION
ISSN1063-6919
页码19447-19456
DOI10.1109/CVPR52733.2024.01839
摘要Recently, 3D Gaussian Splatting has demonstrated impressive novel view synthesis results, reaching high fidelity and efficiency. However, strong artifacts can be observed when changing the sampling rate, e.g., by changing focal length or camera distance. We find that the source for this phenomenon can be attributed to the lack of 3D frequency constraints and the usage of a 2D dilation filter. To address this problem, we introduce a 3D smoothing filter to constrains the size of the 3D Gaussian primitives based on the maximal sampling frequency induced by the input views. It eliminates high-frequency artifacts when zooming in. Moreover, replacing 2D dilation with a 2D Mip filter, which simulates a 2D box filter, effectively mitigates aliasing and dilation issues. Our evaluation, including scenarios such a training on single-scale images and testing on multiple scales, validates the effectiveness of our approach. © 2024 IEEE.
会议名称2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2024
会议地点Seattle, WA, United states
会议日期June 16, 2024 - June 22, 2024
URL查看原文
收录类别EI
语种英语
出版者IEEE Computer Society
EI入藏号20244317260443
原始文献类型Conference article (CA)
引用统计
正在获取...
文献类型会议论文
条目标识符https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/442544
专题信息科学与技术学院_博士生
通讯作者Chen, Anpei
作者单位
1.University of Tübingen, Germany
2.Tübingen Ai Center, Germany
3.ShanghaiTech University, China
4.Czech Technical University, Prague, Czech Republic
推荐引用方式
GB/T 7714
Yu, Zehao,Chen, Anpei,Huang, Binbin,et al. Mip-Splatting: Alias-Free 3D Gaussian Splatting[C]:IEEE Computer Society,2024:19447-19456.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
个性服务
查看访问统计
谷歌学术
谷歌学术中相似的文章
[Yu, Zehao]的文章
[Chen, Anpei]的文章
[Huang, Binbin]的文章
百度学术
百度学术中相似的文章
[Yu, Zehao]的文章
[Chen, Anpei]的文章
[Huang, Binbin]的文章
必应学术
必应学术中相似的文章
[Yu, Zehao]的文章
[Chen, Anpei]的文章
[Huang, Binbin]的文章
相关权益政策
暂无数据
收藏/分享
文件名: 10.1109@CVPR52733.2024.01839.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。