DyGASR: Dynamic Generalized Exponential Splatting with Surface Alignment for Accelerated 3D Mesh Reconstruction

TL;DR

DyGASR introduces a novel method for accelerated 3D mesh reconstruction by using generalized exponential splatting, surface regularization, and dynamic resolution adjustment, achieving faster speed and lower memory usage.

Contribution

It proposes DyGASR, combining generalized exponential functions, surface regularization, and dynamic resolution strategies to improve 3D mesh reconstruction efficiency and accuracy over existing methods.

Findings

25% increase in reconstruction speed

30% reduction in memory usage

Enhanced surface alignment and mesh quality

Abstract

Recent advancements in 3D Gaussian Splatting (3DGS), which lead to high-quality novel view synthesis and accelerated rendering, have remarkably improved the quality of radiance field reconstruction. However, the extraction of mesh from a massive number of minute 3D Gaussian points remains great challenge due to the large volume of Gaussians and difficulty of representation of sharp signals caused by their inherent low-pass characteristics. To address this issue, we propose DyGASR, which utilizes generalized exponential function instead of traditional 3D Gaussian to decrease the number of particles and dynamically optimize the representation of the captured signal. In addition, it is observed that reconstructing mesh with Generalized Exponential Splatting(GES) without modifications frequently leads to failures since the generalized exponential distribution centroids may not precisely align with the scene surface. To overcome this, we adopt Sugar's approach and introduce Generalized Surface Regularization (GSR), which reduces the smallest scaling vector of each point cloud to zero and ensures normal alignment perpendicular to the surface, facilitating subsequent Poisson surface mesh reconstruction. Additionally, we propose a dynamic resolution adjustment strategy that utilizes a cosine schedule to gradually increase image resolution from low to high during the training stage, thus avoiding constant full resolution, which significantly boosts the reconstruction speed. Our approach surpasses existing 3DGS-based mesh reconstruction methods, as evidenced by extensive evaluations on various scene datasets, demonstrating a 25\% increase in speed, and a 30\% reduction in memory usage.