Mip-Splatting: Alias-Free 3D Gaussian Splatting

doi:10.1109/CVPR52733.2024.01839

	Mip-Splatting: Alias-Free 3D Gaussian Splatting
	Yu, Zehao 1,2; Chen, Anpei 1,2; Huang, Binbin3 ; Sattler, Torsten 4; Geiger, Andreas 1,2
	2024
会议录名称	PROCEEDINGS OF THE IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION
ISSN	1063-6919
页码	19447-19456
DOI	10.1109/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.