GScomp-QA: A Subjective Dataset for Quality Assessment of Compressed Gaussian Splatting

2026-05-26

AI Summary

This work addresses the absence of a dedicated subjective quality assessment benchmark for compressed 3D Gaussian Splatting (GS), which hinders accurate evaluation of its perceptual impact. To bridge this gap, the authors introduce GScomp-QA, the first subjective quality dataset tailored to compressed GS, comprising 331 videos generated by nine state-of-the-art compression methods across 13 real-world scenes. Using uncompressed GS renderings as references, reliable subjective scores were collected through psychophysical experiments involving 20 human observers. The dataset effectively disentangles compression-induced distortions from inherent GS rendering artifacts, thereby exposing the limitations of existing objective quality metrics under GS-specific distortions. GScomp-QA is publicly released to serve as an authoritative benchmark for perceptual evaluation of GS compression algorithms and to foster the development of specialized quality assessment metrics.

Abstract

Gaussian Splatting (GS) has emerged as an efficient representation for high-quality 3D reconstruction and novel view synthesis. However, its large model size poses challenges for storage and transmission. While several GS compression solutions have been proposed, their perceptual impact remains poorly understood due to the lack of dedicated evaluation datasets. To address this gap, this paper introduces GScomp-QA, a subjective quality assessment dataset for evaluating synthesis quality from compressed GS models. The dataset comprises 331 video stimuli from 13 real-world scenes, covering 9 state-of-the-art GS compression solutions. By using videos synthesized from uncompressed models as reference, GScomp-QA isolates compression-induced distortions from synthesis artifacts. A subjective study with 20 participants was conducted, providing reliable perceptual scores. Based on these data, GS compression solutions are evaluated through perceptual rate-distortion analysis. In addition, 18 objective quality metrics are evaluated, showing that they do not fully capture GS-specific distortions. GScomp-QA will be publicly available and provide a benchmark for evaluating GS compression solutions and supporting the development of quality metrics tailored to GS compression.

Problem

• Gaussian Splatting
• compression
• quality assessment
• subjective evaluation
• 3D reconstruction

Innovation

• Gaussian Splatting
• compression
• subjective quality assessment
• perceptual evaluation
• rate-distortion analysis