# SpatialQ: Understanding 3D Gaussian Splatting Scene Quality via Visual-based MLLM

arXiv: https://arxiv.org/abs/2607.26595 · HTML: https://mlsanity.com/paper/2607.26595/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 30 of its 46 references that are in the map.
- First posted on arXiv 29 Jul 2026.

## Builds on (most cited first, 30 of 30)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields](https://mlsanity.com/paper/2111.12077/) (2021)
- [Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling](https://mlsanity.com/paper/2412.05271/) (2024)
- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025)
- [MUSIQ: Multi-scale Image Quality Transformer](https://mlsanity.com/paper/2108.05997/) (2021)
- [Exploring CLIP for Assessing the Look and Feel of Images](https://mlsanity.com/paper/2207.12396/) (2022)
- [Image Quality Assessment: Unifying Structure and Texture Similarity](https://mlsanity.com/paper/2004.07728/) (2020)
- [DeepSeek-VL: Towards Real-World Vision-Language Understanding](https://mlsanity.com/paper/2403.05525/) (2024)
- [Scaffold-GS: Structured 3D Gaussians for View-Adaptive Rendering](https://mlsanity.com/paper/2312.00109/) (2023)
- [Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels](https://mlsanity.com/paper/2312.17090/) (2023)
- [LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS](https://mlsanity.com/paper/2311.17245/) (2023)
- [Blind Image Quality Assessment Using A Deep Bilinear Convolutional Neural Network](https://mlsanity.com/paper/1907.02665/) (2019)
- [mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models](https://mlsanity.com/paper/2408.04840/) (2024)
- [Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspective](https://mlsanity.com/paper/2303.14968/) (2023)
- [HAC: Hash-grid Assisted Context for 3D Gaussian Splatting Compression](https://mlsanity.com/paper/2403.14530/) (2024)
- [No-Reference Image Quality Assessment via Transformers, Relative Ranking, and Self-Consistency](https://mlsanity.com/paper/2108.06858/) (2021)
- [Recent Advances in 3D Gaussian Splatting](https://mlsanity.com/paper/2403.11134/) (2024)
- [CompGS: Smaller and Faster Gaussian Splatting with Vector Quantization](https://mlsanity.com/paper/2311.18159/) (2023)
- [Fast Feedforward 3D Gaussian Splatting Compression](https://mlsanity.com/paper/2410.08017/) (2024)
- [MM-PCQA: Multi-Modal Learning for No-reference Point Cloud Quality Assessment](https://mlsanity.com/paper/2209.00244/) (2022)
- [Quality Assessment in the Era of Large Models: A Survey](https://mlsanity.com/paper/2409.00031/) (2024)
- [Compact 3D Gaussian Splatting for Static and Dynamic Radiance Fields](https://mlsanity.com/paper/2408.03822/) (2024)
- [Reasoning as Representation: Rethinking Visual Reinforcement Learning in Image Quality Assessment](https://mlsanity.com/paper/2510.11369/) (2025)
- [A Benchmark for Gaussian Splatting Compression and Quality Assessment Study](https://mlsanity.com/paper/2407.14197/) (2024)
- [Explicit-NeRF-QA: A Quality Assessment Database for Explicit NeRF Model Compression](https://mlsanity.com/paper/2407.08165/) (2024)
- [3DGS-IEval-15K: A Large-scale Image Quality Evaluation Database for 3D Gaussian-Splatting](https://mlsanity.com/paper/2506.14642/) (2025)
- [NeRF-QA: Neural Radiance Fields Quality Assessment Database](https://mlsanity.com/paper/2305.03176/) (2023)
- [Stochasticity-aware No-Reference Point Cloud Quality Assessment](https://mlsanity.com/paper/2401.08926/) (2024)
- [Perceptual Quality Assessment of 3D Gaussian Splatting: A Subjective Dataset and Prediction Metric](https://mlsanity.com/paper/2511.08032/) (2025)

## Abstract (arXiv)

3D Gaussian Splatting (3DGS) has emerged as an effective representation for novel view synthesis and 3D scene reconstruction, creating an increasing demand for reliable quality assessment. Unlike conventional image quality assessment (IQA), the quality of a 3DGS scene depends not only on the perceptual fidelity of rendered views, but also on scene-level factors such as spatial structure and cross-view consistency. Existing IQA methods are limited by their reliance on 2D perceptual cues, whereas general multimodal large language models (MLLMs) are not designed for stable quality regression and may produce unreliable judgments. To address these limitations, a multimodal quality assessment framework is developed for 3DGS scene understanding. First, a 3D-aware quality representation learning framework is introduced by augmenting a VGGT-based encoder with a dedicated quality head. Multi-view images are encoded into view-specific features and aggregated to capture cross-view consistency, while geometric cues are incorporated through joint modeling of depth and point-cloud-related structural information, enabling the learning of structure-aware quality representations beyond appearance-driven features. Second, a grounded multimodal reasoning mechanism is constructed by jointly feeding original images, depth maps, point cloud renderings, and camera parameters into a Qwen-based MLLM.