GSta: Efficient Training Scheme with Siestaed Gaussians for Monocular 3D Scene Reconstruction

• URL: http://arxiv.org/abs/2504.06716v1
• Date: Wed, 09 Apr 2025 09:17:56 GMT
• Title: GSta: Efficient Training Scheme with Siestaed Gaussians for Monocular 3D Scene Reconstruction
• Authors: Anil Armagan, Albert Saà-Garriga, Bruno Manganelli, Kyuwon Kim, M. Kerim Yucel,
• Abstract summary: Gaussian Splatting (GS) is a popular approach for 3D reconstruction.<n>It suffers from large storage and memory requirements.<n>We propose GSta that identifies Gaussians that have converged well during training.
• Score: 4.865050337780373
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Gaussian Splatting (GS) is a popular approach for 3D reconstruction, mostly due to its ability to converge reasonably fast, faithfully represent the scene and render (novel) views in a fast fashion. However, it suffers from large storage and memory requirements, and its training speed still lags behind the hash-grid based radiance field approaches (e.g. Instant-NGP), which makes it especially difficult to deploy them in robotics scenarios, where 3D reconstruction is crucial for accurate operation. In this paper, we propose GSta that dynamically identifies Gaussians that have converged well during training, based on their positional and color gradient norms. By forcing such Gaussians into a siesta and stopping their updates (freezing) during training, we improve training speed with competitive accuracy compared to state of the art. We also propose an early stopping mechanism based on the PSNR values computed on a subset of training images. Combined with other improvements, such as integrating a learning rate scheduler, GSta achieves an improved Pareto front in convergence speed, memory and storage requirements, while preserving quality. We also show that GSta can improve other methods and complement orthogonal approaches in efficiency improvement; once combined with Trick-GS, GSta achieves up to 5x faster training, 16x smaller disk size compared to vanilla GS, while having comparable accuracy and consuming only half the peak memory. More visualisations are available at https://anilarmagan.github.io/SRUK-GSta.

Related papers

• Improving Adaptive Density Control for 3D Gaussian Splatting [3.2248805768155835]
  3D Gaussian Splatting is one of the most influential works in the past year. It faces challenges to properly manage the number of Gaussian primitives that are used during scene reconstruction. We propose three new improvements to the adaptive density control mechanism.
  arXiv  Detail & Related papers  (2025-03-18T14:09:10Z)
• Trick-GS: A Balanced Bag of Tricks for Efficient Gaussian Splatting [4.11274012475378]
  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.
  arXiv  Detail & Related papers  (2025-01-24T14:40:40Z)
• Turbo-GS: Accelerating 3D Gaussian Fitting for High-Quality Radiance Fields [28.047692891923585]
  Novel-view synthesis is an important problem in computer vision with applications in 3D reconstruction, mixed reality, and robotics. Recent methods like 3D Gaussian Splatting (3DGS) have become the preferred method for this task, providing high-quality novel views in real time. Our goal is to reduce the optimization time by training for fewer steps while maintaining high rendering quality.
  arXiv  Detail & Related papers  (2024-12-18T06:46:40Z)
• Speedy-Splat: Fast 3D Gaussian Splatting with Sparse Pixels and Sparse Primitives [60.217580865237835]
  3D Gaussian Splatting (3D-GS) is a recent 3D scene reconstruction technique that enables real-time rendering of novel views by modeling scenes as parametric point clouds of differentiable 3D Gaussians. We identify and address two key inefficiencies in 3D-GS to substantially improve rendering speed. Our Speedy-Splat approach combines these techniques to accelerate average rendering speed by a drastic $mathit6.71times$ across scenes from the Mip-NeRF 360, Tanks & Temples, and Deep Blending datasets.
  arXiv  Detail & Related papers  (2024-11-30T20:25:56Z)
• 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)
• 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)
• PUP 3D-GS: Principled Uncertainty Pruning for 3D Gaussian Splatting [59.277480452459315]
  We propose a principled sensitivity pruning score that preserves visual fidelity and foreground details at significantly higher compression ratios.<n>We also propose a multi-round prune-refine pipeline that can be applied to any pretrained 3D-GS model without changing its training pipeline.
  arXiv  Detail & Related papers  (2024-06-14T17:53:55Z)
• 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)
• EAGLES: Efficient Accelerated 3D Gaussians with Lightweight EncodingS [40.94643885302646]
  3D Gaussian splatting (3D-GS) has gained popularity in novel-view scene synthesis. It addresses the challenges of lengthy training times and slow rendering speeds associated with Radiance Neural Fields (NeRFs) We present a technique utilizing quantized embeddings to significantly reduce per-point memory storage requirements.
  arXiv  Detail & Related papers  (2023-12-07T18:59:55Z)

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.