AA-Splat: Anti-Aliased Feed-forward Gaussian Splatting
Taewoo Suh, Sungpyo Kim, Jongmin Park, Munchurl Kim

TL;DR
AA-Splat introduces an anti-aliased Gaussian splatting method that significantly improves rendering quality for 3D reconstruction and view synthesis across various resolutions by addressing aliasing artifacts.
Contribution
It proposes a novel anti-aliased Gaussian splatting model with an opacity-balanced band-limiting design, enhancing robustness and rendering quality in 3D scene synthesis.
Findings
Achieves 5.4 to 7.5 dB PSNR improvements over DepthSplat.
Effectively eliminates degenerate Gaussians and aliasing artifacts.
Maintains high-quality rendering across resolutions from 4x to 1/4x.
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
