Trick-GS: A Balanced Bag of Tricks for Efficient Gaussian Splatting

• URL: http://arxiv.org/abs/2501.14534v1
• Date: Fri, 24 Jan 2025 14:40:40 GMT
• Title: Trick-GS: A Balanced Bag of Tricks for Efficient Gaussian Splatting
• Abstract summary: Gaussian splatting (GS) for 3D reconstruction has become quite popular due to their fast training, inference speeds and high quality reconstruction.<n>However, GS-based reconstructions generally consist of millions of Gaussians, which makes them hard to use on computationally constrained devices such as smartphones.<n>Trick-GS takes a large step towards resource-constrained GS, where faster run-time, smaller and faster-convergence of models is of paramount concern.
• Score: 4.11274012475378
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Gaussian splatting (GS) for 3D reconstruction has become quite popular due to their fast training, inference speeds and high quality reconstruction. However, GS-based reconstructions generally consist of millions of Gaussians, which makes them hard to use on computationally constrained devices such as smartphones. In this paper, we first propose a principled analysis of advances in efficient GS methods. Then, we propose Trick-GS, which is a careful combination of several strategies including (1) progressive training with resolution, noise and Gaussian scales, (2) learning to prune and mask primitives and SH bands by their significance, and (3) accelerated GS training framework. Trick-GS takes a large step towards resource-constrained GS, where faster run-time, smaller and faster-convergence of models is of paramount concern. Our results on three datasets show that Trick-GS achieves up to 2x faster training, 40x smaller disk size and 2x faster rendering speed compared to vanilla GS, while having comparable accuracy.

Related papers

• Laplacian Frequency Hierarchies for Efficient 3D Gaussian Splatting Training [10.003234443699606]
  A key bottleneck in 3D Gaussian Splatting training is the continual growth of Gaussian primitives.<n>We propose Laplacian Frequency Hierarchies, a simple yet efficient 3DGS scheme that combines Laplacian image decomposition with coarse-to-fine, frequency-staged training.<n>It achieves average speedups of 1.73x and 1.21x at 1K setting, and 1.74x and 1.33x at 4K setting on Taming-3DGS and FastGS.
  arXiv  Detail & Related papers  (2026-09-03T03:46:49Z)
• FastGS: Training 3D Gaussian Splatting in 100 Seconds [15.1354395071878]
  We propose FastGS, a novel, simple, and general acceleration framework.<n>It fully considers the importance of each Gaussian based on multi-view consistency.<n>It efficiently solves the trade-off between training time and rendering quality.
  arXiv  Detail & Related papers  (2025-11-06T11:21:16Z)
• BalanceGS: Algorithm-System Co-design for Efficient 3D Gaussian Splatting Training on GPU [14.147819226084627]
  3DGS has emerged as a promising 3D reconstruction technique.<n>We introduce BalanceGS, the algorithm-system co-design for efficient training in 3DGS.<n>Our approach achieves a 1.44$times$ training speedup on a NVIDIA A100 GPU with negligible quality degradation.
  arXiv  Detail & Related papers  (2025-10-16T11:16:58Z)
• GS-2DGS: Geometrically Supervised 2DGS for Reflective Object Reconstruction [51.99776072246151]
  We propose a novel reconstruction method called GS-2DGS for reflective objects based on 2D Gaussian Splatting (2DGS)<n> Experimental results on synthetic and real datasets demonstrate that our method significantly outperforms Gaussian-based techniques in terms of reconstruction and relighting.
  arXiv  Detail & Related papers  (2025-06-16T05:40:16Z)
• Second-order Optimization of Gaussian Splats with Importance Sampling [51.95046424364725]
  3D Gaussian Splatting (3DGS) is widely used for novel view rendering due to its high quality and fast inference time. We propose a novel second-order optimization strategy based on Levenberg-Marquardt (LM) and Conjugate Gradient (CG) Our method achieves a $3times$ speedup over standard LM and outperforms Adam by $6times$ when the Gaussian count is low.
  arXiv  Detail & Related papers  (2025-04-17T12:52:08Z)
• GSta: Efficient Training Scheme with Siestaed Gaussians for Monocular 3D Scene Reconstruction [4.865050337780373]
  Gaussian Splatting (GS) is a popular approach for 3D reconstruction. It suffers from large storage and memory requirements. We propose GSta that identifies Gaussians that have converged well during training.
  arXiv  Detail & Related papers  (2025-04-09T09:17:56Z)
• CityGaussianV2: Efficient and Geometrically Accurate Reconstruction for Large-Scale Scenes [53.107474952492396]
  CityGaussianV2 is a novel approach for large-scale scene reconstruction. We implement a decomposed-gradient-based densification and depth regression technique to eliminate blurry artifacts and accelerate convergence. Our method strikes a promising balance between visual quality, geometric accuracy, as well as storage and training costs.
  arXiv  Detail & Related papers  (2024-11-01T17:59:31Z)
• LP-3DGS: Learning to Prune 3D Gaussian Splatting [71.97762528812187]
  We propose learning-to-prune 3DGS, where a trainable binary mask is applied to the importance score that can find optimal pruning ratio automatically. Experiments have shown that LP-3DGS consistently produces a good balance that is both efficient and high quality.
  arXiv  Detail & Related papers  (2024-05-29T05:58:34Z)
• DOGS: Distributed-Oriented Gaussian Splatting for Large-Scale 3D Reconstruction Via Gaussian Consensus [56.45194233357833]
  We propose DoGaussian, a method that trains 3DGS distributedly. Our method accelerates the training of 3DGS by 6+ times when evaluated on large-scale scenes.
  arXiv  Detail & Related papers  (2024-05-22T19:17:58Z)
• GaussianPro: 3D Gaussian Splatting with Progressive Propagation [49.918797726059545]
  3DGS relies heavily on the point cloud produced by Structure-from-Motion (SfM) techniques. We propose a novel method that applies a progressive propagation strategy to guide the densification of the 3D Gaussians. Our method significantly surpasses 3DGS on the dataset, exhibiting an improvement of 1.15dB in terms of PSNR.
  arXiv  Detail & Related papers  (2024-02-22T16:00:20Z)
• GES: Generalized Exponential Splatting for Efficient Radiance Field Rendering [112.16239342037714]
  GES (Generalized Exponential Splatting) is a novel representation that employs Generalized Exponential Function (GEF) to model 3D scenes. With the aid of a frequency-modulated loss, GES achieves competitive performance in novel-view synthesis benchmarks.
  arXiv  Detail & Related papers  (2024-02-15T17:32:50Z)

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.