AAA-Gaussians: Anti-Aliased and Artifact-Free 3D Gaussian Rendering
This addresses rendering quality issues in 3D reconstruction for real-time applications, representing an incremental improvement over existing methods.
The paper tackled aliasing, projection artifacts, and view inconsistencies in 3D Gaussian Splatting by incorporating full 3D evaluation of Gaussians, achieving state-of-the-art quality on in-distribution sets and outperforming others for out-of-distribution views.
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.