Perceptual Quality Assessment of 3D Gaussian Splatting: A Subjective Dataset and Prediction Metric

• URL: http://arxiv.org/abs/2511.08032v1
• Date: Wed, 12 Nov 2025 01:35:19 GMT
• Title: Perceptual Quality Assessment of 3D Gaussian Splatting: A Subjective Dataset and Prediction Metric
• Authors: Zhaolin Wan, Yining Diao, Jingqi Xu, Hao Wang, Zhiyang Li, Xiaopeng Fan, Wangmeng Zuo, Debin Zhao,
• Abstract summary: We present 3DGS-QA, the first subjective quality assessment dataset for 3DGS.<n>It comprises 225 degraded reconstructions across 15 object types, enabling a controlled investigation of common distortion factors.<n>Our model extracts spatial and photometric cues from the Gaussian representation to estimate perceived quality in a structure-aware manner.
• Score: 76.66966098297986
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: With the rapid advancement of 3D visualization, 3D Gaussian Splatting (3DGS) has emerged as a leading technique for real-time, high-fidelity rendering. While prior research has emphasized algorithmic performance and visual fidelity, the perceptual quality of 3DGS-rendered content, especially under varying reconstruction conditions, remains largely underexplored. In practice, factors such as viewpoint sparsity, limited training iterations, point downsampling, noise, and color distortions can significantly degrade visual quality, yet their perceptual impact has not been systematically studied. To bridge this gap, we present 3DGS-QA, the first subjective quality assessment dataset for 3DGS. It comprises 225 degraded reconstructions across 15 object types, enabling a controlled investigation of common distortion factors. Based on this dataset, we introduce a no-reference quality prediction model that directly operates on native 3D Gaussian primitives, without requiring rendered images or ground-truth references. Our model extracts spatial and photometric cues from the Gaussian representation to estimate perceived quality in a structure-aware manner. We further benchmark existing quality assessment methods, spanning both traditional and learning-based approaches. Experimental results show that our method consistently achieves superior performance, highlighting its robustness and effectiveness for 3DGS content evaluation. The dataset and code are made publicly available at https://github.com/diaoyn/3DGSQA to facilitate future research in 3DGS quality assessment.

Related papers

• MUGSQA: Novel Multi-Uncertainty-Based Gaussian Splatting Quality Assessment Method, Dataset, and Benchmarks [50.53294970211443]
  Gaussian Splatting (GS) has emerged as a promising technique for 3D object reconstruction, delivering high-quality rendering results with significantly improved reconstruction speed.<n> assessing the perceptual quality of 3D objects reconstructed with different GS-based methods remains an open challenge.<n>We 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.<n>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.
  arXiv  Detail & Related papers  (2025-11-10T08:21:11Z)
• Visibility-Aware Densification for 3D Gaussian Splatting in Dynamic Urban Scenes [7.253732091582086]
  VAD-GS is a 3DGS framework tailored for geometry recovery in challenging urban scenes.<n>Our method identifies unreliable geometry structures via voxel-based visibility reasoning.<n>It selects informative supporting views through diversity-aware view selection, and recovers missing structures via patch matching-based stereo reconstruction.
  arXiv  Detail & Related papers  (2025-10-10T13:22:12Z)
• Hi3DEval: Advancing 3D Generation Evaluation with Hierarchical Validity [78.7107376451476]
  Hi3DEval is a hierarchical evaluation framework tailored for 3D generative content.<n>We extend texture evaluation beyond aesthetic appearance by explicitly assessing material realism.<n>We propose a 3D-aware automated scoring system based on hybrid 3D representations.
  arXiv  Detail & Related papers  (2025-08-07T17:50:13Z)
• 3DGS-IEval-15K: A Large-scale Image Quality Evaluation Database for 3D Gaussian-Splatting [38.666247000427674]
  3DGS has emerged as a promising approach for novel view synthesis, offering real-time rendering with high visual fidelity.<n>We present 3DGS-IEval-15K, the first large-scale image quality assessment (IQA) dataset specifically designed for compressed 3DGS representations.
  arXiv  Detail & Related papers  (2025-06-17T15:39:34Z)
• Generating Synthetic Stereo Datasets using 3D Gaussian Splatting and Expert Knowledge Transfer [16.040335263873278]
  We introduce a 3D Gaussian Splatting (3DGS)-based pipeline for stereo dataset generation, offering an efficient alternative to Neural Radiance Fields (NeRF)-based methods.<n>We find that when fine-tuning stereo models on 3DGS-generated datasets, we demonstrate competitive performance in zero-shot generalization benchmarks.
  arXiv  Detail & Related papers  (2025-06-05T11:41:09Z)
• EVolSplat: Efficient Volume-based Gaussian Splatting for Urban View Synthesis [61.1662426227688]
  Existing NeRF and 3DGS-based methods show promising results in achieving photorealistic renderings but require slow, per-scene optimization.<n>We introduce EVolSplat, an efficient 3D Gaussian Splatting model for urban scenes that works in a feed-forward manner.
  arXiv  Detail & Related papers  (2025-03-26T02:47:27Z)
• GS-QA: Comprehensive Quality Assessment Benchmark for Gaussian Splatting View Synthesis [4.117347527143616]
  Gaussian Splatting (GS) offers a promising alternative to Neural Radiance Fields (NeRF) for real-time 3D scene rendering.<n>GS achieves faster rendering times and reduced memory consumption compared to the neural network approach used in NeRF.<n>This paper describes a subjective quality assessment study that aims to evaluate synthesized videos obtained with several static GS methods.
  arXiv  Detail & Related papers  (2025-02-18T17:46:57Z)
• PF3plat: Pose-Free Feed-Forward 3D Gaussian Splatting [54.7468067660037]
  PF3plat sets a new state-of-the-art across all benchmarks, supported by comprehensive ablation studies validating our design choices.<n>Our framework capitalizes on fast speed, scalability, and high-quality 3D reconstruction and view synthesis capabilities of 3DGS.
  arXiv  Detail & Related papers  (2024-10-29T15:28:15Z)
• 3DGCQA: A Quality Assessment Database for 3D AI-Generated Contents [50.730468291265886]
  This paper introduces a novel 3DGC quality assessment dataset, 3DGCQA, built using 7 representative Text-to-3D generation methods. The visualization intuitively reveals the presence of 6 common distortion categories in the generated 3DGCs. subjective quality assessment is conducted by evaluators, whose ratings reveal significant variation in quality across different generation methods. Several objective quality assessment algorithms are tested on the 3DGCQA dataset.
  arXiv  Detail & Related papers  (2024-09-11T12:47:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.