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

• URL: http://arxiv.org/abs/2511.06830v1
• Date: Mon, 10 Nov 2025 08:21:11 GMT
• Title: MUGSQA: Novel Multi-Uncertainty-Based Gaussian Splatting Quality Assessment Method, Dataset, and Benchmarks
• Authors: Tianang Chen, Jian Jin, Shilv Cai, Zhuangzi Li, Weisi Lin,
• Abstract summary: 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.
• Score: 50.53294970211443
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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 benchmark code will be released soon.

Related papers

• Appreciate the View: A Task-Aware Evaluation Framework for Novel View Synthesis [15.922599086027098]
  Novel View Synthesis (NVS) aims to generate realistic images of a given content from unseen viewpoints.<n>Existing evaluation metrics struggle to assess whether a generated image is both realistic and faithful to the source view.<n>We introduce two complementary evaluation metrics: a reference-based score, $D_textPRISM$, and a reference-free score, $textMMD_textPRISM$.
  arXiv  Detail & Related papers  (2025-11-16T16:28:08Z)
• OUGS: Active View Selection via Object-aware Uncertainty Estimation in 3DGS [14.124481717283544]
  OUGS is a principled, physically-grounded uncertainty formulation for 3DGS.<n>Our core innovation is to derive uncertainty directly from the explicit physical parameters of the 3D Gaussian primitives.<n>This foundation allows us to then seamlessly integrate semantic segmentation masks to produce a targeted, object-aware uncertainty score.
  arXiv  Detail & Related papers  (2025-11-12T15:08:46Z)
• Perceptual Quality Assessment of 3D Gaussian Splatting: A Subjective Dataset and Prediction Metric [76.66966098297986]
  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.
  arXiv  Detail & Related papers  (2025-11-11T09:34:20Z)
• D$^2$GS: Depth-and-Density Guided Gaussian Splatting for Stable and Accurate Sparse-View Reconstruction [73.61056394880733]
  3D Gaussian Splatting (3DGS) enables real-time, high-fidelity novel view synthesis (NVS) with explicit 3D representations.<n>We identify two key failure modes under sparse-view conditions: overfitting in regions with excessive Gaussian density near the camera, and underfitting in distant areas with insufficient Gaussian coverage.<n>We propose a unified framework D$2$GS, comprising two key components: a Depth-and-Density Guided Dropout strategy, and a Distance-Aware Fidelity Enhancement module.
  arXiv  Detail & Related papers  (2025-10-09T17:59:49Z)
• 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)
• Evaluating Robustness of Monocular Depth Estimation with Procedural Scene Perturbations [55.4735586739093]
  We introduce PDE, a new benchmark which enables systematic robustness evaluation.<n>PDE uses procedural generation to create 3D scenes that test robustness to various controlled perturbations.<n>Our analysis yields interesting findings on what perturbations are challenging for state-of-the-art depth models.
  arXiv  Detail & Related papers  (2025-07-01T17:33:48Z)
• GTR: Gaussian Splatting Tracking and Reconstruction of Unknown Objects Based on Appearance and Geometric Complexity [49.31257173003408]
  We present a novel method for 6-DoF object tracking and high-quality 3D reconstruction from monocular RGBD video.<n>Our approach demonstrates strong capabilities in recovering high-fidelity object meshes, setting a new standard for single-sensor 3D reconstruction in open-world environments.
  arXiv  Detail & Related papers  (2025-05-17T08:46:29Z)
• 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)
• Stochasticity-aware No-Reference Point Cloud Quality Assessment [27.27917013945021]
  Previous works consistently regard point cloud quality assessment (PCQA) as a regression problem.<n>This work presents the first probabilistic architecture for no-reference PCQA, motivated by the labeling process of existing datasets.
  arXiv  Detail & Related papers  (2024-01-17T02:25:42Z)
• Iterative Optimization of Pseudo Ground-Truth Face Image Quality Labels [0.0]
  Face image quality assessment (FIQA) techniques provide sample quality information that can be used to reject poor quality data. We propose a quality label optimization approach, which incorporates sample-quality information from mated-pair similarities into quality predictions. We evaluate the proposed approach using three state-of-the-art FIQA methods over three diverse datasets.
  arXiv  Detail & Related papers  (2022-08-31T08:24:09Z)
• Regression or Classification? New Methods to Evaluate No-Reference Picture and Video Quality Models [45.974399400141685]
  We propose two new methods to evaluate and compare no-reference quality models at coarser levels. We conduct a benchmark experiment of popular no-reference quality models on recent in-the-wild picture and video quality datasets.
  arXiv  Detail & Related papers  (2021-01-30T05:40:14Z)

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.