# Turbo-GS: Accelerating 3D Gaussian Fitting for High-Quality Radiance Fields arXiv: https://arxiv.org/abs/2412.13547 ยท HTML: https://mlsanity.com/paper/2412.13547/ ## Key facts - Cited by 8 papers in the map (data through 14 Oct 2026). - Builds on 48 of its 54 references that are in the map. - First posted on arXiv 18 Dec 2024. ## Builds on (most cited first, 30 of 48) - [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) - [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022) - [Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields](https://mlsanity.com/paper/2111.12077/) (2021) - [Plenoxels: Radiance Fields without Neural Networks](https://mlsanity.com/paper/2112.05131/) (2021) - [TensoRF: Tensorial Radiance Fields](https://mlsanity.com/paper/2203.09517/) (2022) - [2D Gaussian Splatting for Geometrically Accurate Radiance Fields](https://mlsanity.com/paper/2403.17888/) (2024) - [Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstruction](https://mlsanity.com/paper/2111.11215/) (2021) - [PlenOctrees for Real-time Rendering of Neural Radiance Fields](https://mlsanity.com/paper/2103.14024/) (2021) - [Scaffold-GS: Structured 3D Gaussians for View-Adaptive Rendering](https://mlsanity.com/paper/2312.00109/) (2023) - [pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction](https://mlsanity.com/paper/2312.12337/) (2023) - [Mip-Splatting: Alias-free 3D Gaussian Splatting](https://mlsanity.com/paper/2311.16493/) (2023) - [SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering](https://mlsanity.com/paper/2311.12775/) (2023) - [MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images](https://mlsanity.com/paper/2403.14627/) (2024) - [Point-NeRF: Point-based Neural Radiance Fields](https://mlsanity.com/paper/2201.08845/) (2022) - [LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS](https://mlsanity.com/paper/2311.17245/) (2023) - [GS-LRM: Large Reconstruction Model for 3D Gaussian Splatting](https://mlsanity.com/paper/2404.19702/) (2024) - [gsplat: An Open-Source Library for Gaussian Splatting](https://mlsanity.com/paper/2409.06765/) (2024) - [No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images](https://mlsanity.com/paper/2410.24207/) (2024) - [Octree-GS: Towards Consistent Real-time Rendering with LOD-Structured 3D Gaussians](https://mlsanity.com/paper/2403.17898/) (2024) - [BakedSDF: Meshing Neural SDFs for Real-Time View Synthesis](https://mlsanity.com/paper/2302.14859/) (2023) - [3D Gaussian Splatting as Markov Chain Monte Carlo](https://mlsanity.com/paper/2404.09591/) (2024) - [A Hierarchical 3D Gaussian Representation for Real-Time Rendering of Very Large Datasets](https://mlsanity.com/paper/2406.12080/) (2024) - [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) - [EAGLES: Efficient Accelerated 3D Gaussians with Lightweight EncodingS](https://mlsanity.com/paper/2312.04564/) (2023) - [LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias](https://mlsanity.com/paper/2410.17242/) (2024) - [Reducing the Memory Footprint of 3D Gaussian Splatting](https://mlsanity.com/paper/2406.17074/) (2024) - [CompGS: Smaller and Faster Gaussian Splatting with Vector Quantization](https://mlsanity.com/paper/2311.18159/) (2023) - [Revising Densification in Gaussian Splatting](https://mlsanity.com/paper/2404.06109/) (2024) ## Built on by (most cited first, 8 of 8) - [AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Views](https://mlsanity.com/paper/2505.23716/) (2025) - [iLRM: An Iterative Large 3D Reconstruction Model](https://mlsanity.com/paper/2507.23277/) (2025) - [Hybrid 3D-4D Gaussian Splatting for Fast Dynamic Scene Representation](https://mlsanity.com/paper/2505.13215/) (2025) - [ContraGS: Codebook-Condensed and Trainable Gaussian Splatting for Fast, Memory-Efficient Reconstruction](https://mlsanity.com/paper/2509.03775/) (2025) - [GSta: Efficient Training Scheme with Siestaed Gaussians for Monocular 3D Scene Reconstruction](https://mlsanity.com/paper/2504.06716/) (2025) - [Fix False Transparency by Noise Guided Splatting](https://mlsanity.com/paper/2510.15736/) (2025) - [UniC-Lift: Unified 3D Instance Segmentation via Contrastive Learning](https://mlsanity.com/paper/2512.24763/) (2025) - [RoboPearls: Editable Video Simulation for Robot Manipulation](https://mlsanity.com/paper/2506.22756/) (2025) ## Abstract (arXiv) Novel-view synthesis plays a crucial role in computer vision with applications in 3D reconstruction, mixed reality, and robotics. Recent approaches, such as 3D Gaussian Splatting (3DGS), have emerged as state-of-the-art solutions, offering high-quality novel view synthesis in real time. However, training 3DGS models remains slow, particularly for high-resolution images, often requiring hours to fit a scene with 200 views. In this work, we aim to accelerate the fitting process by reducing computational overhead and improving learning efficiency. Specifically, we introduce a dilated rendering technique that renders only a subset of pixels instead of the full image, significantly reducing computational costs. To enhance learning efficiency, we develop a convergence-aware budget control mechanism that balances the addition of new Gaussians with the optimization of existing ones. Additionally, to improve densification efficiency and prevent gradient vanishing, we incorporate both positional and appearance errors to improve the effectiveness of densification. With these improvements, we achieve fast 4K-resolution fitting while maintaining, or even improving, novel view rendering quality. Extensive experiments demonstrate that our method achieves significantly faster optimization than existing approaches while preserving high rendering fidelity.