Explicit-NeRF-QA: A Quality Assessment Database for Explicit NeRF Model Compression

TL;DR

This paper introduces Explicit-NeRF-QA, a comprehensive dataset for assessing the quality of explicit NeRF models, highlighting the need for better no-reference metrics and providing valuable data for future research in NeRF compression and quality evaluation.

Contribution

The paper constructs a new dataset with subjective and objective quality assessments for explicit NeRF models, addressing the lack of standardized benchmarks in NeRF compression.

Findings

High correlation (around 0.85) with full-reference metrics.

No-reference metrics show poor correlation (0.4-0.6).

Dataset is publicly available for further research.

Abstract

In recent years, Neural Radiance Fields (NeRF) have demonstrated significant advantages in representing and synthesizing 3D scenes. Explicit NeRF models facilitate the practical NeRF applications with faster rendering speed, and also attract considerable attention in NeRF compression due to its huge storage cost. To address the challenge of the NeRF compression study, in this paper, we construct a new dataset, called Explicit-NeRF-QA. We use 22 3D objects with diverse geometries, textures, and material complexities to train four typical explicit NeRF models across five parameter levels. Lossy compression is introduced during the model generation, pivoting the selection of key parameters such as hash table size for InstantNGP and voxel grid resolution for Plenoxels. By rendering NeRF samples to processed video sequences (PVS), a large scale subjective experiment with lab environment is conducted to collect subjective scores from 21 viewers. The diversity of content, accuracy of mean opinion scores (MOS), and characteristics of NeRF distortion are comprehensively presented, establishing the heterogeneity of the proposed dataset. The state-of-the-art objective metrics are tested in the new dataset. Best Person correlation, which is around 0.85, is collected from the full-reference objective metric. All tested no-reference metrics report very poor results with 0.4 to 0.6 correlations, demonstrating the need for further development of more robust no-reference metrics. The dataset, including NeRF samples, source 3D objects, multiview images for NeRF generation, PVSs, MOS, is made publicly available at the following location: https://github.com/YukeXing/Explicit-NeRF-QA.