MipSLAM: Alias-Free Gaussian Splatting SLAM

TL;DR

MipSLAM is introduced, a frequency-aware 3D Gaussian Splatting (3DGS) SLAM framework capable of high-fidelity anti-aliased novel view synthesis and robust pose estimation under varying camera configurations and an Elliptical Adaptive Anti-aliasing (EAA) algorithm that approximates Gaussian contributions via geometry-aware numerical integration, avoiding costly analytic computation.

Abstract

This paper introduces MipSLAM, a frequency-aware 3D Gaussian Splatting (3DGS) SLAM framework capable of high-fidelity anti-aliased novel view synthesis and robust pose estimation under varying camera configurations. Existing 3DGS-based SLAM systems often suffer from aliasing artifacts and trajectory drift due to inadequate filtering and purely spatial optimization. To overcome these limitations, we propose an Elliptical Adaptive Anti-aliasing (EAA) algorithm that approximates Gaussian contributions via geometry-aware numerical integration, avoiding costly analytic computation. Furthermore, we present a Spectral-Aware Pose Graph Optimization (SA-PGO) module that reformulates trajectory estimation in the frequency domain, effectively suppressing high-frequency noise and drift through graph Laplacian analysis. A novel local frequency-domain perceptual loss is also introduced to enhance fine-grained geometric detail recovery. Extensive evaluations on Replica and TUM datasets demonstrate that MipSLAM achieves state-of-the-art rendering quality and localization accuracy across multiple resolutions while maintaining real-time capability. Code is available at https://github.com/yzli1998/MipSLAM.

Figures (6)

• Figure 1: Our method reformulates pixel rendering as a continuous integration process via stratified importance sampling, ensuring antialiasing quality and computational efficiency. The dashed ellipses depict Gaussian principal axes, color-coded by condition number: red (high), orange (moderate), purple (boundary enhancement), and green (low complexity).
• Figure 2: MipSLAM tracks RGB-D streams, estimates per-frame poses, selects keyframes, and projects Gaussian primitives into a global map. It incrementally computes 3D filter scales, compares rendered and GT RGB-D in a sliding window, and jointly optimizes poses and maps via gradient backpropagation. For $\alpha$-blending, we use elliptical projection and condition number analysis to reduce aliasing via numerical integration. SA-PGO corrects localization drift from anti-aliasing, and a local frequency loss improves texture perception.
• Figure 3: SA-PGO leverages frequency-domain trajectory analysis and graph spectral theory to achieve adaptive noise suppression and intelligent spectral-aware optimization.
• Figure 4: Qualitative explanation on frequency-domain loss $\mathcal{L}_{fla}$. We partitioned the depth map into multiple patches and individually constrained amplitude and phase within each patch, yielding enhanced local details.
• Figure 5: Testing results at 1$/$4 resolution on the Replica b25 and TUM datasets b26. Previous methods have exhibited varying degrees of aliasing, blurring, and inflation issues. Our MipSLAM can faithfully represent the real world.