MUGSQA: Novel Multi-Uncertainty-Based Gaussian Splatting Quality Assessment Method, Dataset, and Benchmarks
This addresses the problem of quality assessment for 3D reconstruction in computer vision, providing a dataset and benchmarks for researchers, but it is incremental as it builds on existing Gaussian Splatting techniques.
The paper tackles the challenge of assessing perceptual quality in 3D objects reconstructed with Gaussian Splatting methods by proposing a multi-distance subjective quality assessment method and constructing the MUGSQA dataset with multiple uncertainties, including input view quantity and resolution, to evaluate reconstruction robustness and quality metrics.
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 benchmark code will be released soon.