Alias-free 4D Gaussian Splatting

TL;DR

This paper introduces a novel method for 4D Gaussian Splatting that adaptively regulates sampling frequency, eliminating artifacts and reducing redundancies in dynamic scene reconstruction, thereby improving rendering quality.

Contribution

We derive a maximum sampling frequency formulation and propose a scale-adaptive filter with a scale loss to enhance 4D Gaussian Splatting for dynamic scene reconstruction.

Findings

Eliminates high-frequency artifacts at increased rendering frequencies.

Reduces redundant Gaussians in multi-view video reconstruction.

Validates effectiveness through monocular and multi-view experiments.

Abstract

Existing dynamic scene reconstruction methods based on Gaussian Splatting enable real-time rendering and generate realistic images. However, adjusting the camera's focal length or the distance between Gaussian primitives and the camera to modify rendering resolution often introduces strong artifacts, stemming from the frequency constraints of 4D Gaussians and Gaussian scale mismatch induced by the 2D dilated filter. To address this, we derive a maximum sampling frequency formulation for 4D Gaussian Splatting and introduce a 4D scale-adaptive filter and scale loss, which flexibly regulates the sampling frequency of 4D Gaussian Splatting. Our approach eliminates high-frequency artifacts under increased rendering frequencies while effectively reducing redundant Gaussians in multi-view video reconstruction. We validate the proposed method through monocular and multi-view video reconstruction experiments.Ours project page: https://4d-alias-free.github.io/4D-Alias-free/