cs.CVNov 5, 2026

AffineGS: Unlocking Accurate Geometry in 3DGS via Spatially Varying Affine Rectification

Authors: Tze Ho Elden Tse, Jizong Peng, Richard Chen, Angela Yao

Organizations: 1dConstruct Robotics · 2National University of Singapore

Abstract

3D Gaussian Splatting (3DGS) has become the leading approach for photorealistic novel view synthesis, yet its geometric accuracy lags behind its visual quality. Existing depth-guided methods attempt to resolve this by regularizing the optimization with monocular depth priors, typically using a single global scale-and-shift alignment. Crucially, we discover a fundamental flaw in this assumption: modern monocular depth networks systematically exhibit region-dependent, piecewise-linear distortions. This discovery invalidates standard global alignment strategies, which warp scene geometry by enforcing a single transform. To address this, we introduce a spatially varying affine rectification model that corrects monocular disparity into consistent metric depth using regionally smooth, edge-aware fields. We further derive a normal-aware regularizer that uses spatial gradients to couple the rectified disparity with 3DGS depth and normals. Across diverse experimental settings, our sensor-free method shows strong photometric quality of Gaussian Splatting while substantially improving geometric accuracy and outperforming state-of-the art geometry-focused methods.

Figures & tables

Appendix figures & tables15 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. In Depth We Trust: Reliable Monocular Depth Supervision for Gaussian Splatting

    Apr 7, 2026Wenhui Xiao, Ethan Goan, Rodrigo Santa Cruz +43D Gaussian Splatting

  2. DepthGS: Depth-Guided Gaussian Splatting with Adaptive Regularization for High-Quality Surface Reconstruction

    Nov 10, 2026Xiao Ren, Yu Liu, Ning An +43D Gaussian SplattingMulti-View 3D Reconstruction

  3. GeoGSplat: Geometry-Grounded Non-Pixel-Aligned Gaussian Splatting

    Oct 27, 2026Jiale Wang, Chen Zhao, Haoyang Zhang +63D Gaussian SplattingNovel View Synthesis