AA-Splat: Anti-Aliased Feed-forward Gaussian Splatting

Abstract

Feed-forward 3D Gaussian Splatting (FF-3DGS) emerges as a fast and robust solution for sparse-view 3D reconstruction and novel view synthesis (NVS). However, existing FF-3DGS methods are built on incorrect screen-space dilation filters, causing severe rendering artifacts when rendering at out-of-distribution sampling rates. We firstly propose an FF-3DGS model, called AA-Splat, to enable robust anti-aliased rendering at any resolution. AA-Splat utilizes an opacity-balanced band-limiting (OBBL) design, which combines two components: a 3D band-limiting post-filter integrates multi-view maximal frequency bounds into the feed-forward reconstruction pipeline, effectively band-limiting the resulting 3D scene representations and eliminating degenerate Gaussians; an Opacity Balancing (OB) to seamlessly integrate all pixel-aligned Gaussian primitives into the rendering process, compensating for the increased overlap between expanded Gaussian primitives. AA-Splat demonstrates drastic improvements with average 5.4$\sim$7.5dB PSNR gains on NVS performance over a state-of-the-art (SOTA) baseline, DepthSplat, at all resolutions, between $4\times$ and $1/4\times$. Code will be made available.

Figures (8)

• Figure 1: Our AA-Splat is the first feed-forward 3DGS framework for alias-free rendering. Built upon the DepthSplat xu2025depthsplat architecture, AA-Splat employs Opacity Balanced Band Limiting (OBBL) combining 3D band-limiting post-filter (3D-BLPF) and opacity balancing (OB). This enables robust, high-fidelity reconstruction at out-of-distribution scales (1/4× to 4× resolution). While the baseline DepthSplat xu2025depthsplat suffers from severe erosion and dilation artifacts when zooming (changing sampling rates), AA-Splat consistently produces sharp, anti-aliased results.
• Figure 2: Overview of AA-Splat. After unprojecting per-view depth maps to obtain the 3D Gaussian centers, the maximal frequency bound of each 3D Gaussian primitive is computed from context view camera poses and focal lengths, which is then converted to its 3D band-limiting Gaussian post-filter. The GS head predicts the residual Gaussian parameters which are then post-filtered by the 3D filters to obtain the band-limited 3D Gaussians. During rendering, opacity balancing (OB) compensates for the increase in overlap between pixel-aligned Gaussian primitives for improved photometric supervision and rendering fidelity.
• Figure 3: Multi-scale visual comparison on RE10K zhou2018stereo.$\times4$ indicates rendering target views at higher resolution to simulate zoom-in effects, while $\times1/4$ indicates rendering target views at lower resolution to simulate zoom-out effects. Additional visualizations will be available in supplementary materials.
• Figure 4: Multi-scale visual comparison of cross-dataset generalization on ACID liu2021infinite. Models trained on RE10K are directly used to test on scenes from ACID. Additional visualizations will be available in supplementary materials.
• Figure 5: Ablation results on the DL3DV ling2024dl3dv dataset. All methods are trained and inferred at full resolution and rendered at $4\times$ resolution to mimic zoom-in. Removing either OB or 3D-BLPF causes unnatural grid-like artifacts or sharp jagged edges. Our method (AA-Splat) effectively suppresses these rendering artifacts.