AAA-Gaussians: Anti-Aliased and Artifact-Free 3D Gaussian Rendering

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Steiner, Michael, Köhler, Thomas, Radl, Lukas, Windisch, Felix, Schmalstieg, Dieter, Steinberger, Markus
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866911086443233280
author Steiner, Michael
Köhler, Thomas
Radl, Lukas
Windisch, Felix
Schmalstieg, Dieter
Steinberger, Markus
author_facet Steiner, Michael
Köhler, Thomas
Radl, Lukas
Windisch, Felix
Schmalstieg, Dieter
Steinberger, Markus
contents Although 3D Gaussian Splatting (3DGS) has revolutionized 3D reconstruction, it still faces challenges such as aliasing, projection artifacts, and view inconsistencies, primarily due to the simplification of treating splats as 2D entities. We argue that incorporating full 3D evaluation of Gaussians throughout the 3DGS pipeline can effectively address these issues while preserving rasterization efficiency. Specifically, we introduce an adaptive 3D smoothing filter to mitigate aliasing and present a stable view-space bounding method that eliminates popping artifacts when Gaussians extend beyond the view frustum. Furthermore, we promote tile-based culling to 3D with screen-space planes, accelerating rendering and reducing sorting costs for hierarchical rasterization. Our method achieves state-of-the-art quality on in-distribution evaluation sets and significantly outperforms other approaches for out-of-distribution views. Our qualitative evaluations further demonstrate the effective removal of aliasing, distortions, and popping artifacts, ensuring real-time, artifact-free rendering.
format Preprint
id arxiv_https___arxiv_org_abs_2504_12811
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle AAA-Gaussians: Anti-Aliased and Artifact-Free 3D Gaussian Rendering
Steiner, Michael
Köhler, Thomas
Radl, Lukas
Windisch, Felix
Schmalstieg, Dieter
Steinberger, Markus
Graphics
Computer Vision and Pattern Recognition
Although 3D Gaussian Splatting (3DGS) has revolutionized 3D reconstruction, it still faces challenges such as aliasing, projection artifacts, and view inconsistencies, primarily due to the simplification of treating splats as 2D entities. We argue that incorporating full 3D evaluation of Gaussians throughout the 3DGS pipeline can effectively address these issues while preserving rasterization efficiency. Specifically, we introduce an adaptive 3D smoothing filter to mitigate aliasing and present a stable view-space bounding method that eliminates popping artifacts when Gaussians extend beyond the view frustum. Furthermore, we promote tile-based culling to 3D with screen-space planes, accelerating rendering and reducing sorting costs for hierarchical rasterization. Our method achieves state-of-the-art quality on in-distribution evaluation sets and significantly outperforms other approaches for out-of-distribution views. Our qualitative evaluations further demonstrate the effective removal of aliasing, distortions, and popping artifacts, ensuring real-time, artifact-free rendering.
title AAA-Gaussians: Anti-Aliased and Artifact-Free 3D Gaussian Rendering
topic Graphics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2504.12811