PAGaS: Pixel-Aligned 1DoF Gaussian Splatting for Depth Refinement

TL;DR

PAGaS introduces a pixel-aligned 1DoF Gaussian Splatting method that enhances depth refinement in multi-view stereo by constraining Gaussian parameters, leading to more detailed 3D reconstructions.

Contribution

It adapts Gaussian Splatting for depth refinement by modeling pixel depth with constrained 1DoF Gaussians, improving geometric fidelity in multi-view stereo.

Findings

Produces highly detailed depth maps

Outperforms baseline methods on 3D reconstruction benchmarks

Maintains Gaussian constraints during optimization

Abstract

Gaussian Splatting (GS) has emerged as an efficient approach for high-quality novel view synthesis. While early GS variants struggled to accurately model the scene's geometry, recent advancements constraining the Gaussians' spread and shapes, such as 2D Gaussian Splatting, have significantly improved geometric fidelity. In this paper, we present Pixel-Aligned 1DoF Gaussian Splatting (PAGaS) that adapts the GS representation from novel view synthesis to the multi-view stereo depth task. Our key contribution is modeling a pixel's depth using one-degree-of-freedom (1DoF) Gaussians that remain tightly constrained during optimization. Unlike existing approaches, our Gaussians' positions and sizes are restricted by the back-projected pixel volumes, leaving depth as the sole degree of freedom to optimize. PAGaS produces highly detailed depths, as illustrated in Figure 1. We quantitatively validate these improvements on top of reference geometric and learning-based multi-view stereo baselines on challenging 3D reconstruction benchmarks. Code: davidrecasens.github.io/pagas