English

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

Computer Vision and Pattern Recognition 2026-04-01 v1

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\sim7.5dB PSNR gains on NVS performance over a state-of-the-art (SOTA) baseline, DepthSplat, at all resolutions, between 4×4\times and 1/4×1/4\times. Code will be made available.

Keywords

Cite

@article{arxiv.2603.29394,
  title  = {AA-Splat: Anti-Aliased Feed-forward Gaussian Splatting},
  author = {Taewoo Suh and Sungpyo Kim and Jongmin Park and Munchurl Kim},
  journal= {arXiv preprint arXiv:2603.29394},
  year   = {2026}
}

Comments

Please visit our project page at https://kaist-viclab.github.io/aasplat-site/