cs.CVNov 19, 2026

PaveSplat: Resolution-Robust Feed-Forward Gaussian Splatting with Residually Corrected Surface-Aligned Covariances

Authors: Janghun Kim, Hyun-Cheol Kim, Eunbin An, Myeonghun Oh, Hyon-Gon Choo

Organizations: ETRI, South Korea

Abstract

We present PaveSplat, a feed-forward Gaussian splatting method that adds a learned residual to the analytic surface-aligned covariance, keeping surfels paving the visible surface across rendering resolutions. Pixel-aligned feed-forward Gaussian splatting predicts one primitive per pixel from a few images in a single pass, and its rendering quality depends on how well these primitives cover the surface. Recent surfel-based methods compute the surface-aligned covariance analytically from predicted depth. However, this covariance has no way to correct the surfel orientation where the depth-derived frame is ill-posed. The surfels then cover the surface loosely; at the training resolution each surfel's one-pixel minimum footprint covers the gaps, but they show up as holes when the same prediction is re-rendered at a higher resolution. To address this, we keep the analytic covariance as an initialization, with its axes aligned to the surface tangents, and add an identity-initialized unit-quaternion residual that reorients a surfel only where this improves rendering, turning surfels that the analytic frame mis-aims back onto the surface. On RealEstate10K, PaveSplat achieves the best PSNR, SSIM, and LPIPS among single-Gaussian-per-pixel methods at every scale (1x-8x). The native-resolution gain is small; the benefit appears when the same prediction is rendered at higher display resolutions without re-running the network. On zero-shot DL3DV, it leads PSNR within this group at every scale and ranks first or second on SSIM/LPIPS. A coverage-hole analysis shows fewer uncovered pixels than both baselines under high-resolution re-rendering.

Figures & tables

Explore similar work

CardsList
  1. PCAsplat: Gaussian Splatting with Local PCA Regularization

    Oct 7, 2026Vitor Matias, Filipe Nascimento, Kiyohiro Nakayama +63D Gaussian SplattingPoint Cloud Surface Reconstruction

  2. RoSplat: Robust Feed-Forward Pixel-wise Gaussian Splatting for Varying Input Views and High-Resolution Rendering

    May 13, 2026Hoang Chuong Nguyen, Renjie Wu, Jose M. Alvarez +13D Gaussian SplattingNovel View Synthesis

  3. ZipSplat: Fewer Gaussians, Better Splats

    Jun 3, 2026Alexander Veicht, Sunghwan Hong, Dániel Baráth +13D Gaussian SplattingMulti-View 3D Reconstruction