Mip-Splatting: Alias-Free 3D Gaussian Splatting
Zehao Yu, Anpei Chen, Binbin Huang, Torsten Sattler, Andreas Geiger
摘要
splatting (c) Zoom-out of (a) Erosion (Brake cable too thin) 3D Object 3D Gaussian Camera Center Image Plane (Screen Space) Decreased Focal length Increased Focal length 2D Gaussian Dilated 2D Gaussian 5 Pixels Brightening High frequency artifacts due to degenerate (thin) 3D Gaussians Dilation (Spokes too thick due to screen space dilation) Faithful Rendering Faithful Rendering (a) Faithful Representation (b) Degenerate Representation (d) Zoom-in of (b) Figure 1. 3D Gaussian Splatting [18] renders images by representing 3D Objects as 3D Gaussians which are projected onto the image plane followed by 2D Dilation in screen space as shown in (a). Its intrinsic shrinkage bias leads to degenerate 3D Gaussians that exceed the sampling limit as illustrated by the δ function in (b) while rendering similarly in 2D due to the dilation operation. However, when changing the sampling rate (via the focal length or camera distance), we observe strong dilation effects (c) and high frequency artifacts (d).
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper301
- 3D Gaussian Splatting as Markov Chain Monte CarloShakiba Kheradmand, Daniel Rebain, Gopal Sharma, Weiwei Sun 等NeurIPS 2024 · 被引用 285 次
- Segment Anything in 3D with NeRFsJiazhong Cen, Zanwei Zhou, Jiemin Fang, Chen Yang 等NeurIPS 2023 · 被引用 255 次
- GaussianPro: 3D Gaussian Splatting with Progressive PropagationKai Cheng, Xiaoxiao Long, Kaizhi Yang, Yao Yao 等ICML 2024 · 被引用 241 次
- WildGaussians: 3D Gaussian Splatting In the WildJonas Kulhanek, Songyou Peng, Zuzana Kukelova, Marc Pollefeys 等NeurIPS 2024 · 被引用 202 次
- A Hierarchical 3D Gaussian Representation for Real-Time Rendering of Very Large DatasetsBernhard Kerbl, Andreas Meuleman, Georgios Kopanas, Michael Wimmer 等SIGGRAPH 2024 · 被引用 180 次
它引用的顶会 Paper26
- 3D Gaussian Splatting for Real-Time Radiance Field RenderingBernhard Kerbl, Georgios Kopanas, Thomas Leimkühler, George DrettakisSIGGRAPH 2023 · 被引用 5,687 次
- Instant neural graphics primitives with a multiresolution hash encodingThomas Müller, Alex Evans, Christoph Schied, Alexander KellerSIGGRAPH 2022 · 被引用 4,089 次
- Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance FieldsJonathan T. Barron, Ben Mildenhall, Matthew Tancik, Peter Hedman 等ICCV 2021 · 被引用 2,700 次
- Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance FieldsJonathan T. Barron, Ben Mildenhall, Dor Verbin, Pratul P. Srinivasan 等CVPR 2022 · 被引用 1,603 次
- Neural Sparse Voxel FieldsLingjie Liu, Jiatao Gu, Kyaw Zaw Lin, Tat-Seng Chua 等NeurIPS 2020 · 被引用 1,535 次
相关 Paper
- AAA-Gaussians: Anti-Aliased and Artifact-Free 3D Gaussian RenderingMichael Steiner, Thomas Köhler, Lukas Radl, Felix Windisch 等ICCV 2025 · 被引用 5 次
- Anti-Aliased 2D Gaussian SplattingMae Younes, Adnane BoukhaymaNeurIPS 2025 · 被引用 9 次
- Multi-Scale 3D Gaussian Splatting for Anti-Aliased RenderingZhiwen Yan, Weng Fei Low, Yu Chen, Gim Hee LeeCVPR 2024 · 被引用 77 次
- Gaussian Blending: Rethinking Alpha Blending in 3D Gaussian SplattingJunseo Koo, Jinseo Jeong, Gunhee KimAAAI 2026
- Deformable Radial Kernel SplattingYi-Hua Huang, Ming-Xian Lin, Yang-Tian Sun, Ziyi Yang 等CVPR 2025
