# Gauss What You Need: Compact Gaussian Splatting Across Scene Scales

arXiv: https://arxiv.org/abs/2609.31248 · HTML: https://mlsanity.com/paper/2609.31248/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 34 references that are in the map.
- First posted on arXiv 25 Sep 2026.

## Builds on (most cited first, 27 of 27)

- [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)
- [Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fields](https://mlsanity.com/paper/2304.06706/) (2023)
- [Mega-NeRF: Scalable Construction of Large-Scale NeRFs for Virtual Fly-Throughs](https://mlsanity.com/paper/2112.10703/) (2021)
- [Compact 3D Gaussian Representation for Radiance Field](https://mlsanity.com/paper/2311.13681/) (2023)
- [Mini-Splatting: Representing Scenes with a Constrained Number of Gaussians](https://mlsanity.com/paper/2403.14166/) (2024)
- [Taming 3DGS: High-Quality Radiance Fields with Limited Resources](https://mlsanity.com/paper/2406.15643/) (2024)
- [Capturing, Reconstructing, and Simulating: the UrbanScene3D Dataset](https://mlsanity.com/paper/2107.04286/) (2021)
- [Speedy-Splat: Fast 3D Gaussian Splatting with Sparse Pixels and Sparse Primitives](https://mlsanity.com/paper/2412.00578/) (2024)
- [AbsGS: Recovering Fine Details for 3D Gaussian Splatting](https://mlsanity.com/paper/2404.10484/) (2024)
- [LP-3DGS: Learning to Prune 3D Gaussian Splatting](https://mlsanity.com/paper/2405.18784/) (2024)
- [FastGS: Training 3D Gaussian Splatting in 100 Seconds](https://mlsanity.com/paper/2511.04283/) (2025)
- [DashGaussian: Optimizing 3D Gaussian Splatting in 200 Seconds](https://mlsanity.com/paper/2503.18402/) (2025)
- [Steepest Descent Density Control for Compact 3D Gaussian Splatting](https://mlsanity.com/paper/2505.05587/) (2025)
- [Perceptual-GS: Scene-adaptive Perceptual Densification for Gaussian Splatting](https://mlsanity.com/paper/2506.12400/) (2025)
- [Gradient-Direction-Aware Density Control for 3D Gaussian Splatting](https://mlsanity.com/paper/2508.09239/) (2025)
- [ConeGS: Error-Guided Densification Using Pixel Cones for Improved Reconstruction With Fewer Primitives](https://mlsanity.com/paper/2511.06810/) (2025)
- [Prune Wisely, Reconstruct Sharply: Compact 3D Gaussian Splatting via Adaptive Pruning and Difference-of-Gaussian Primitives](https://mlsanity.com/paper/2602.24136/) (2026)
- [RLGS: Reinforcement Learning-Based Adaptive Hyperparameter Tuning for Gaussian Splatting](https://mlsanity.com/paper/2508.04078/) (2025)
- [ControlGS: Consistent Structural Compression Control for Deployment-Aware Gaussian Splatting](https://mlsanity.com/paper/2505.10473/) (2025)
- [Beyond Heuristics: Learnable Density Control for 3D Gaussian Splatting](https://mlsanity.com/paper/2605.00408/) (2026)
- [BlitzGS: City-Scale Gaussian Splatting at Lightning Speed](https://mlsanity.com/paper/2605.13794/) (2026)
- [Signal Structure-Aware Gaussian Splatting for Large-Scale Scene Reconstruction](https://mlsanity.com/paper/2607.01698/) (2026)
- [SPARE-GS: Structural Parsimony and Resource Efficiency for 3D Gaussian Splatting](https://mlsanity.com/paper/2607.16624/) (2026)
- [GS^2: Graph-based Spatial Distribution Optimization for Compact 3D Gaussian Splatting](https://mlsanity.com/paper/2604.01884/) (2026)
- [Smart target point control for Gaussian Splatting methods](https://mlsanity.com/paper/2605.16158/) (2026)

## Abstract (arXiv)

3D Gaussian Splatting reconstructs a scene as a collection of Gaussian primitives from a set of posed photographs called the capture. The number of primitives used to represent the scene affects reconstruction quality, storage, and rendering cost. How to select this number automatically across capture scales remains unresolved: configurations effective on standard benchmarks can leave larger captures with too few Gaussians to reconstruct fine details. We observe that the surface to represent, given by the capture's extent and resolution, is known before training, whereas its content complexity becomes apparent during training, through the reconstruction quality on the training views. We introduce TangoGS, which combines capture-derived model sizing with training-based adaptation: the capture determines the scale of the model, and training feedback determines its final size within that scale. Before training, TangoGS derives a learning allowance for model growth from the capture's total pixels after discounting views that re-observe the same scene points. During training, reconstruction quality guides how many Gaussians to add and remove. On 13 standard benchmark scenes, TangoGS matches the mean PSNR of the best-performing evaluated baseline, LeGS, with 48% fewer Gaussians. On eight large captures, the same configuration automatically scales to larger models when necessary, achieving the highest mean PSNR among evaluated methods: 0.54 dB above the runner-up with 2.3× as many Gaussians. Together, capture-derived learning allowances and training-quality guided density control enable a state-of-the-art quality--size compromise across scene scales without retuning.