Novel View Synthesis with Gaussian Splatting: Impact on Photogrammetry Model Accuracy and Resolution

TL;DR

This study compares photogrammetry and Gaussian Splatting for 3D reconstruction and view synthesis, demonstrating how Gaussian Splatting enhances novel view generation and improves model accuracy and resolution.

Contribution

The paper introduces a modified Gaussian Splatting method for rendering high-quality novel views and integrates it into photogrammetry workflows for improved 3D model accuracy.

Findings

Gaussian Splatting produces higher quality novel views.

Augmented datasets with Gaussian Splatting improve photogrammetry models.

Enhanced Gaussian Splatting enables better resolution and model detail.

Abstract

In this paper, I present a comprehensive study comparing Photogrammetry and Gaussian Splatting techniques for 3D model reconstruction and view synthesis. I created a dataset of images from a real-world scene and constructed 3D models using both methods. To evaluate the performance, I compared the models using structural similarity index (SSIM), peak signal-to-noise ratio (PSNR), learned perceptual image patch similarity (LPIPS), and lp/mm resolution based on the USAF resolution chart. A significant contribution of this work is the development of a modified Gaussian Splatting repository, which I forked and enhanced to enable rendering images from novel camera poses generated in the Blender environment. This innovation allows for the synthesis of high-quality novel views, showcasing the flexibility and potential of Gaussian Splatting. My investigation extends to an augmented dataset that includes both original ground images and novel views synthesized via Gaussian Splatting. This augmented dataset was employed to generate a new photogrammetry model, which was then compared against the original photogrammetry model created using only the original images. The results demonstrate the efficacy of using Gaussian Splatting to generate novel high-quality views and its potential to improve photogrammetry-based 3D reconstructions. The comparative analysis highlights the strengths and limitations of both approaches, providing valuable information for applications in extended reality (XR), photogrammetry, and autonomous vehicle simulations. Code is available at https://github.com/pranavc2255/gaussian-splatting-novel-view-render.git.