# Proxy-GS: Unified Occlusion Priors for Training and Inference in Structured 3D Gaussian Splatting arXiv: https://arxiv.org/abs/2509.24421 ยท HTML: https://mlsanity.com/paper/2509.24421/ ## Key facts - Cited by 5 papers in the map (data through 14 Oct 2026). - Builds on 38 of its 46 references that are in the map. - First posted on arXiv 29 Sep 2025. ## Builds on (most cited first, 30 of 38) - [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018) - [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023) - [Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields](https://mlsanity.com/paper/2111.12077/) (2021) - [Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields](https://mlsanity.com/paper/2103.13415/) (2021) - [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025) - [NeRF++: Analyzing and Improving Neural Radiance Fields](https://mlsanity.com/paper/2010.07492/) (2020) - [Scaffold-GS: Structured 3D Gaussians for View-Adaptive Rendering](https://mlsanity.com/paper/2312.00109/) (2023) - [Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fields](https://mlsanity.com/paper/2304.06706/) (2023) - [Modular Primitives for High-Performance Differentiable Rendering](https://mlsanity.com/paper/2011.03277/) (2020) - [LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS](https://mlsanity.com/paper/2311.17245/) (2023) - [Compact 3D Gaussian Representation for Radiance Field](https://mlsanity.com/paper/2311.13681/) (2023) - [MapAnything: Universal Feed-Forward Metric 3D Reconstruction](https://mlsanity.com/paper/2509.13414/) (2025) - [Octree-GS: Towards Consistent Real-time Rendering with LOD-Structured 3D Gaussians](https://mlsanity.com/paper/2403.17898/) (2024) - [A Hierarchical 3D Gaussian Representation for Real-Time Rendering of Very Large Datasets](https://mlsanity.com/paper/2406.12080/) (2024) - [VastGaussian: Vast 3D Gaussians for Large Scene Reconstruction](https://mlsanity.com/paper/2402.17427/) (2024) - [CityGaussian: Real-time High-quality Large-Scale Scene Rendering with Gaussians](https://mlsanity.com/paper/2404.01133/) (2024) - [MatrixCity: A Large-scale City Dataset for City-scale Neural Rendering and Beyond](https://mlsanity.com/paper/2309.16553/) (2023) - [GauHuman: Articulated Gaussian Splatting from Monocular Human Videos](https://mlsanity.com/paper/2312.02973/) (2023) - [Neural Kernel Surface Reconstruction](https://mlsanity.com/paper/2305.19590/) (2023) - [FlashGS: Efficient 3D Gaussian Splatting for Large-scale and High-resolution Rendering](https://mlsanity.com/paper/2408.07967/) (2024) - [SpatialLM: Training Large Language Models for Structured Indoor Modeling](https://mlsanity.com/paper/2506.07491/) (2025) - [On Scaling Up 3D Gaussian Splatting Training](https://mlsanity.com/paper/2406.18533/) (2024) - [MaskGaussian: Adaptive 3D Gaussian Representation from Probabilistic Masks](https://mlsanity.com/paper/2412.20522/) (2024) - [Horizon-GS: Unified 3D Gaussian Splatting for Large-Scale Aerial-to-Ground Scenes](https://mlsanity.com/paper/2412.01745/) (2024) - [LetsGo: Large-Scale Garage Modeling and Rendering via LiDAR-Assisted Gaussian Primitives](https://mlsanity.com/paper/2404.09748/) (2024) - [CityGS-X: A Scalable Architecture for Efficient and Geometrically Accurate Large-Scale Scene Reconstruction](https://mlsanity.com/paper/2503.23044/) (2025) - [LODGE: Level-of-Detail Large-Scale Gaussian Splatting with Efficient Rendering](https://mlsanity.com/paper/2505.23158/) (2025) - [GauU-Scene V2: Assessing the Reliability of Image-Based Metrics with Expansive Lidar Image Dataset Using 3DGS and NeRF](https://mlsanity.com/paper/2404.04880/) (2024) - [MVG-Splatting: Multi-View Guided Gaussian Splatting with Adaptive Quantile-Based Geometric Consistency Densification](https://mlsanity.com/paper/2407.11840/) (2024) - [When Gaussian Meets Surfel: Ultra-fast High-fidelity Radiance Field Rendering](https://mlsanity.com/paper/2504.17545/) (2025) ## Built on by (most cited first, 5 of 5) - [Visionary: The World Model Carrier Built on WebGPU-Powered Gaussian Splatting Platform](https://mlsanity.com/paper/2512.08478/) (2025) - [SpaceDG: Benchmarking Spatial Intelligence under Visual Degradation](https://mlsanity.com/paper/2605.22536/) (2026) - [Exploration Matters for Escaping the Blur Trap in 3D Gaussian Splatting](https://mlsanity.com/paper/2607.17965/) (2026) - [RoofGS: Roofline-Guided End-to-End Acceleration of 3D Gaussian Splatting](https://mlsanity.com/paper/2608.15785/) (2026) - [TopoGS: Topology-Aware Anchor Feature Aggregation for Large-Scale 3D Gaussian Splatting](https://mlsanity.com/paper/2609.27868/) (2026) ## Abstract (arXiv) 3D Gaussian Splatting (3DGS) has emerged as an efficient approach for achieving photorealistic rendering. Recent MLP-based variants further improve visual fidelity but introduce substantial decoding overhead during rendering. To alleviate computation cost, several pruning strategies and level-of-detail (LOD) techniques have been introduced, aiming to effectively reduce the number of Gaussian primitives in large-scale scenes. However, our analysis reveals that significant redundancy still remains due to the lack of occlusion awareness. In this work, we propose Proxy-GS, a novel pipeline that exploits a proxy to introduce Gaussian occlusion awareness from any view. At the core of our approach is a fast proxy system capable of producing precise occlusion depth maps at a resolution of 1000x1000 under 1ms. This proxy serves two roles: first, it guides the culling of anchors and Gaussians to accelerate rendering speed. Second, it guides the densification towards surfaces during training, avoiding inconsistencies in occluded regions, and improving the rendering quality. In heavily occluded scenarios, such as the MatrixCity Streets dataset, Proxy-GS not only equips MLP-based Gaussian splatting with stronger rendering capability but also achieves faster rendering speed. Specifically, it achieves more than 2.5x speedup over Octree-GS, and consistently delivers substantially higher rendering quality. Code will be public upon acceptance.