MUGSQA: Novel Multi-Uncertainty-Based Gaussian Splatting Quality Assessment Method, Dataset, and Benchmarks

TL;DR

This paper introduces MUGSQA, a comprehensive dataset and benchmarks for assessing the perceptual quality of Gaussian Splatting 3D reconstructions, considering multiple uncertainties affecting input data and reconstruction robustness.

Contribution

It proposes a multi-distance subjective quality assessment method, constructs the MUGSQA dataset, and establishes benchmarks for robustness and metric performance evaluation.

Findings

MUGSQA dataset captures multiple uncertainties affecting GS reconstructions.

The benchmarks evaluate robustness of GS methods and quality assessment metrics.

The proposed assessment method aligns closely with human perception.

Abstract

Gaussian Splatting (GS) has recently emerged as a promising technique for 3D object reconstruction, delivering high-quality rendering results with significantly improved reconstruction speed. As variants continue to appear, assessing the perceptual quality of 3D objects reconstructed with different GS-based methods remains an open challenge. To address this issue, we first propose a unified multi-distance subjective quality assessment method that closely mimics human viewing behavior for objects reconstructed with GS-based methods in actual applications, thereby better collecting perceptual experiences. Based on it, we also construct a novel GS quality assessment dataset named MUGSQA, which is constructed considering multiple uncertainties of the input data. These uncertainties include the quantity and resolution of input views, the view distance, and the accuracy of the initial point cloud. Moreover, we construct two benchmarks: one to evaluate the robustness of various GS-based reconstruction methods under multiple uncertainties, and the other to evaluate the performance of existing quality assessment metrics. Our dataset and code are available at https://github.com/Solivition/MUGSQA.