Lune

CVPR2024Top-tier venue

Mip-Splatting: Alias-Free 3D Gaussian Splatting

Zehao Yu, Anpei Chen, Binbin Huang, Torsten Sattler, Andreas Geiger

2024Year
360Citations
301Top-tier citations

Abstract

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).

Ask about this paper

Your agent reads all of it.

Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.

Questions to start from

Your agent calls

Luneget_paper_fulltext

Ask in Lune

Free to start. No credit card required.

lune papers fulltext d5083e78-fedd-4085-a6bf-6afd1b46f17e

Cited by top-tier papers301

Ask how each one uses it

Builds on26

Related papers

Dusk over the sea between two cliffs drawn in fine vertical lines