3DGSI-Assessor: A Large-Scale Dataset and An LMM-based Method for 3D Gaussian Splatting Image Quality Assessment

• URL: http://arxiv.org/abs/2608.03279v1
• Date: Tue, 04 Aug 2026 07:53:14 GMT
• Title: 3DGSI-Assessor: A Large-Scale Dataset and An LMM-based Method for 3D Gaussian Splatting Image Quality Assessment
• Abstract summary: We present 3DGS-IEval-15K+, a large-scale, multi-dimensional IQA dataset for compressed 3DGS.<n>Based on 3DGS-IEval-15K+, we propose 3DGSI-Assessor, an all-in-one 3DGS IQA framework.
• Score: 56.721866312037065
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 3D Gaussian Splatting (3DGS) has become a dominant representation for real-time novel view synthesis (NVS), yet its storage footprint makes compression indispensable for practical deployment. 3DGS training and compression introduce representation-specific distortions such as floating artifacts and surface scattering, which conventional image quality assessment (IQA) metrics fail to capture. Moreover, the independent compression of geometric and color attributes may lead to decoupled dimension-specific distortions that must be diagnosed separately, yet existing metrics report only a single overall score. To address these gaps, we present 3DGS-IEval-15K+, a large-scale, multi-dimensional IQA dataset for compressed 3DGS, comprising 15,200 images from 10 diverse scenes, produced by 6 representative 3DGS algorithms at systematically designed compression levels and rendered from 20 strategically selected viewpoints spanning both training views and challenging novel views, annotated with 45,600 mean opinion scores (MOSs) across overall, geometry, and color quality. Based on 3DGS-IEval-15K+, we propose 3DGSI-Assessor, an all-in-one 3DGS IQA framework that integrates global semantic and dimension-specific local features within a large multimodal model (LMM), predicting all three dimensions in a single forward pass. 3DGSI-Assessor achieves state-of-the-art performance on 3DGS-IEval-15K+, and exhibits competitive generalization on other NVS benchmarks. Dataset and code will be released at https://github.com/YukeXing/3DGSI-Assessor.

Related papers

• GETA-3DGS: Automatic Joint Structured Pruning and Quantization for 3D Gaussian Splatting [0.0]
  GETA-3DGS is an end-to-end automatic joint structured pruning and quantization framework for 3DGS.<n>It operates directly on raw Gaussian primitives rather than a post-hoc anchor representation.<n>It delivers 5x storage reduction over Vanilla 3DGS with no per-scene thresholds.
  arXiv  Detail & Related papers  (2026-05-03T23:12:14Z)
• Holi-Spatial: Evolving Video Streams into Holistic 3D Spatial Intelligence [78.1406635199656]
  Holi-Spatial is the first fully automated, large-scale, spatially-aware multimodal dataset constructed from raw video inputs without human intervention.<n>Holi-Spatial-4M is the first large-scale, high-quality 3D semantic dataset, containing 12K optimized 3DGS scenes, 1.3M 2D masks, 320K 3D bounding boxes, 320K instance captions, 1.2M 3D grounding instances, and 1.2M spatial QA pairs.
  arXiv  Detail & Related papers  (2026-03-08T14:49:20Z)
• Splatwizard: A Benchmark Toolkit for 3D Gaussian Splatting Compression [69.94586602640355]
  We introduce Splatwizard, a unified benchmark toolkit designed specifically for 3DGS compression models.<n>Splatwizard provides an easy-to-use framework to implement new 3DGS compression model and utilize state-of-the-art techniques.
  arXiv  Detail & Related papers  (2025-12-31T09:26:04Z)
• Quantile Rendering: Efficiently Embedding High-dimensional Feature on 3D Gaussian Splatting [52.18697134979677]
  Recent advancements in computer vision have successfully extended Open-vocabulary segmentation (OVS) to the 3D domain by leveraging 3D Gaussian Splatting (3D-GS)<n>Existing methods employ codebooks or feature compression, causing information loss, thereby degrading segmentation quality.<n>We introduce Quantile Rendering (Q-Render), a novel rendering strategy for 3D Gaussians that efficiently handles high-dimensional features while maintaining high fidelity.<n>Our framework outperforms state-of-the-art methods, while enabling real-time rendering with an approximate 43.7x speedup on 512-D feature maps.
  arXiv  Detail & Related papers  (2025-12-24T04:16:18Z)
• Unlocking Zero-shot Potential of Semi-dense Image Matching via Gaussian Splatting [20.039403558110354]
  We introduce MatchGS, a framework designed to correct and leverage 3DGS for robust, zero-shot image matching.<n>Our approach is twofold: (1) a geometrically-faithful data generation pipeline that refines 3DGS geometry to produce highly precise correspondence labels, and (2) a 2D-3D representation alignment strategy that infuses 3DGS' explicit 3D knowledge into the 2D matcher.<n>Our generated ground-truth correspondences reduce the epipolar error by up to 40 times compared to existing datasets.
  arXiv  Detail & Related papers  (2025-11-26T10:43:21Z)
• 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)
• 3DGS-VBench: A Comprehensive Video Quality Evaluation Benchmark for 3DGS Compression [9.900921811495213]
  3DGS-VBench is a large-scale Video Quality Assessment (VQA) dataset and Benchmark with 660 compressed 3DGS models and video sequences generated from 11 scenes.<n>We benchmark 6 3DGS compression algorithms on storage efficiency and visual quality, and evaluate 15 quality assessment metrics across multiple paradigms.
  arXiv  Detail & Related papers  (2025-08-09T16:47:19Z)
• 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)
• SAGS: Structure-Aware 3D Gaussian Splatting [53.6730827668389]
  We propose a structure-aware Gaussian Splatting method (SAGS) that implicitly encodes the geometry of the scene. SAGS reflects to state-of-the-art rendering performance and reduced storage requirements on benchmark novel-view synthesis datasets.
  arXiv  Detail & Related papers  (2024-04-29T23:26:30Z)

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.