TurboGS: Accelerating 3D Gaussian Splatting via Error-Guided Sparse Pixel Sampling and Optimization
- URL: http://arxiv.org/abs/2606.15924v1
- Date: Sun, 14 Jun 2026 16:59:48 GMT
- Title: TurboGS: Accelerating 3D Gaussian Splatting via Error-Guided Sparse Pixel Sampling and Optimization
- Abstract summary: TurboGS is an error-guided training framework that accelerates 3DGS by concentrating optimization on perceptually informative pixels.<n>Experiments on standard benchmarks demonstrate that TurboGS can deliver on par or superior rendering quality within 100 seconds on a single 5090 GPU card.
- Score: 54.179316928687435
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Consumer-level applications require fast optimization of 3D Gaussian Splatting (3DGS) with high-fidelity novel view rendering. However, existing 3DGS acceleration approaches still incur substantial computation on redundant pixels while sacrificing fine details. In this paper, we present TurboGS, an error-guided training framework that accelerates 3DGS by concentrating optimization on perceptually informative pixels. TurboGS is built upon four core components: (1) a tile-wise sparse pixel sampling, which, driven by multi-view reconstruction errors during training, prioritizes challenging regions and skips well-reconstructed ones to avoid redundant gradient computation; (2) a tile-wise structure-aware loss with sparse Normalized Cross-Correlation, which provides sparse yet effective supervision to preserve fine details and stabilize training; (3) an error-driven Gaussian density control strategy, which dynamically allocates model capacity and removes redundant primitives; and (4) a tailored hybrid optimizer that couples Hessian-informed updates with Adam moment damping to stabilize and improve convergence under sparse supervision. Experiments on standard benchmarks demonstrate that TurboGS can deliver on par or superior rendering quality within 100 seconds on a single RTX 5090 GPU card (up to 10x training speedup over vanilla 3DGS).
Related papers
- CaT-GS: Efficient 3DGS Rendering for Large Scale Scenes via Inter-frame Caching and Tile Scheduling [29.831227440392635]
CaT-GS is a novel and efficient 3DGS rendering pipeline.<n>It mitigates a speedup of up to 10 times over the original 3DGS and up 70% over previous state-of-the-art methods.
arXiv Detail & Related papers (2026-07-20T11:33:51Z) - GS^2: Graph-based Spatial Distribution Optimization for Compact 3D Gaussian Splatting [50.2045409672451]
3D Gaussian Splatting (3DGS) has demonstrated breakthrough performance in novel view synthesis and real-time rendering.<n>It is constrained by the high memory cost due to a huge number of Gaussian points.<n>We propose graph-based spatial distribution optimization for compact 3DGS.
arXiv Detail & Related papers (2026-04-02T10:41:51Z) - Speedy Deformable 3D Gaussian Splatting: Fast Rendering and Compression of Dynamic Scenes [57.69608119350651]
Recent extensions of 3D Gaussian Splatting (3DGS) to dynamic scenes achieve high-quality novel view synthesis by using neural networks to predict the time-varying deformation of each Gaussian.<n>However, performing per-Gaussian neural inference at every frame poses a significant bottleneck, limiting rendering speed and increasing memory and compute requirements.<n>We present Speedy Deformable 3D Gaussian Splatting (SpeeDe3DGS), a general pipeline for accelerating the rendering speed of dynamic 3DGS and 4DGS representations by reducing neural inference through two complementary techniques.
arXiv Detail & Related papers (2025-06-09T16:30:48Z) - TC-GS: A Faster Gaussian Splatting Module Utilizing Tensor Cores [8.422911585027924]
This paper integrates TC-GS, an algorithm-independent universal module that expands the applicability of Core (TCU) for 3DGS.<n>Our method maintains rendering quality while providing an additional 2.18x speedup over existing Gaussian acceleration algorithms, thereby achieving a total acceleration of up to 5.6x.
arXiv Detail & Related papers (2025-05-30T16:58:18Z) - Steepest Descent Density Control for Compact 3D Gaussian Splatting [72.54055499344052]
3D Gaussian Splatting (3DGS) has emerged as a powerful real-time, high-resolution novel view.<n>We propose a theoretical framework that demystifies and improves density control in 3DGS.<n>We introduce SteepGS, incorporating steepest density control, a principled strategy that minimizes loss while maintaining a compact point cloud.
arXiv Detail & Related papers (2025-05-08T18:41:38Z) - DashGaussian: Optimizing 3D Gaussian Splatting in 200 Seconds [71.37326848614133]
We propose DashGaussian, a scheduling scheme over the optimization complexity of 3DGS.<n>We show that our method accelerates the optimization of various 3DGS backbones by 45.7% on average.
arXiv Detail & Related papers (2025-03-24T07:17:27Z) - LiteGS: A High-performance Framework to Train 3DGS in Subminutes via System and Algorithm Codesign [6.7123686385076615]
3D Gaussian Splatting (3DGS) has emerged as promising alternative in 3D representation, but it still suffers from high training cost.<n>This paper introduces LiteGS, a high performance computation framework that systematically optimize the 3DGS training pipeline.<n> Experimental results demonstrate that LiteGS accelerates the original 3DGS training by up to 13.4x with comparable or superior quality.
arXiv Detail & Related papers (2025-03-03T05:52:02Z) - Taming 3DGS: High-Quality Radiance Fields with Limited Resources [50.92437599516609]
3D Gaussian Splatting (3DGS) has transformed novel-view synthesis with its fast, interpretable, and high-fidelity rendering.
We tackle the challenges of training and rendering 3DGS models on a budget.
We derive faster, numerically equivalent solutions for gradient computation and attribute updates.
arXiv Detail & Related papers (2024-06-21T20:44:23Z)
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.