AdpSplit: Error-Driven Adaptive Splitting for Faster Geometry Discovery in 3D Gaussian Splatting

• URL: http://arxiv.org/abs/2605.06876v1
• Date: Thu, 07 May 2026 19:23:16 GMT
• Title: AdpSplit: Error-Driven Adaptive Splitting for Faster Geometry Discovery in 3D Gaussian Splatting
• Abstract summary: We introduce AdpSplit, an error-driven adaptive split operator that determines the number of split children and initializes the child parameters from L1-pixel-error region statistics.<n>Across the MipNeRF360, Deep-Blending, and Tanks&Temples datasets, AdpSplit reduces the training time of multiple accelerated 3DGS pipelines by 9.2%-22.3%.<n>With FastGS, AdpSplit matches the full-schedule PSNR on MipNeRF360 while reducing training time by 16.4%, corresponding to a 12.6x acceleration over vanilla 3DGS.
• Score: 61.977804325410695
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Adaptive density control in 3D Gaussian Splatting (3DGS) repeatedly grows the Gaussian population through fixed-cardinality random splitting to discover useful scene structure. However, in vanilla 3DGS, its binary split operator requires many densification rounds to expose fine details, making it a bottleneck for efficient training schedules with fewer iterations. We introduce AdpSplit, an error-driven adaptive split operator that determines the number of split children and initializes the child parameters from L1-pixel-error region statistics, enabling fewer densification iterations, thus reduced training time, while preserving the rendering quality of full-schedule training. Across the MipNeRF360, Deep-Blending, and Tanks&Temples datasets, AdpSplit reduces the training time of multiple accelerated 3DGS pipelines by 9.2%-22.3% as a simple drop-in replacement for the standard split operator. With FastGS, AdpSplit matches the full-schedule PSNR on MipNeRF360 while reducing training time by 16.4%, corresponding to a 12.6x acceleration over vanilla 3DGS.

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)
• Splaxel: Efficient Distributed Training of 3D Gaussian Splatting for Large-scale Scene Reconstruction via Pixel-level Communication [23.72228306115471]
  Splaxel is a communication-efficient 3DGS training framework based on pixel-level local rendering and global composition.<n>Spaxel achieves up to 7.6$times$ speedup over the state-of-the-art distributed 3DGS framework.
  arXiv  Detail & Related papers  (2026-06-17T01:27:41Z)
• TurboGS: Accelerating 3D Gaussian Splatting via Error-Guided Sparse Pixel Sampling and Optimization [54.179316928687435]
  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.
  arXiv  Detail & Related papers  (2026-06-14T16:59:48Z)
• KC-3DGS: Kurtosis-Constrained Gaussian Splatting for High-Fidelity View Synthesis [28.10448224660243]
  3D Gaussian Splatting (3DGS) enables real-time novel view synthesis by representing scenes as collections of anisotropic Gaussians optimized via differentiableization.<n>Standard pixel-space losses (L1, SSIM) constrain only aggregate reconstruction error, permitting the optimization to redistribute error across frequency scales.<n>We propose KC-3DGS, which augments 3DGS training with wavelet-domain supervision based on natural image statistics.
  arXiv  Detail & Related papers  (2026-06-02T04:04:24Z)
• SkipGS: Post-Densification Backward Skipping for Efficient 3DGS Training [40.28141759111142]
  3D Gaussian Splatting (3DGS) achieves real-time novel-view synthesis by optimizing millions of anisotropic Gaussians.<n>We propose SkipGS with a novel view-adaptive backward gating mechanism for efficient post-densification training.<n>On Mip-NeRF 360, compared to 3DGS, SkipGS reduces end-to-end training time by 23.1%, driven by a 42.0% reduction in post-densification time.
  arXiv  Detail & Related papers  (2026-03-09T22:32:52Z)
• 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)
• LOBE-GS: Load-Balanced and Efficient 3D Gaussian Splatting for Large-Scale Scene Reconstruction [24.185537949073723]
  3D Gaussian Splatting (3DGS) has established itself as an efficient representation for real-time, high-fidelity 3D scene reconstruction.<n>We introduce LoBE-GS, a novel Load-Balanced and Efficient 3D Gaussian Splatting framework.<n>LoBE-GS consistently achieves up to $2times$ faster end-to-end training time than state-of-the-art baselines.
  arXiv  Detail & Related papers  (2025-10-02T08:02:06Z)
• 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)
• Speedy MASt3R [68.47052557089631]
  MASt3R redefines image matching as a 3D task by leveraging DUSt3R and introducing a fast reciprocal matching scheme.<n>Fast MASt3R achieves a 54% reduction in inference time (198 ms to 91 ms per image pair) without sacrificing accuracy.<n>This advancement enables real-time 3D understanding, benefiting applications like mixed reality navigation and large-scale 3D scene reconstruction.
  arXiv  Detail & Related papers  (2025-03-13T03:56:22Z)
• 3DGS-LM: Faster Gaussian-Splatting Optimization with Levenberg-Marquardt [65.25603275491544]
  We present 3DGS-LM, a new method that accelerates the reconstruction of 3D Gaussian Splatting (3DGS)<n>Our method is 20% faster than the original 3DGS while obtaining the same reconstruction quality optimization.
  arXiv  Detail & Related papers  (2024-09-19T16:31:44Z)
• SparseGS: Real-Time 360° Sparse View Synthesis using Gaussian Splatting [6.506706621221143]
  3D Splatting (3DGS) has recently enabled real-time rendering of 3D scenes for novel view synthesis.<n>This technique requires dense training views to accurately reconstruct 3D geometry.<n>We introduce SparseGS, an efficient training pipeline designed to address the limitations of 3DGS in scenarios with sparse training views.
  arXiv  Detail & Related papers  (2023-11-30T21:38:22Z)
• Exploring the Limits of Differentially Private Deep Learning with Group-wise Clipping [91.60608388479645]
  We show that emphper-layer clipping allows clipping to be performed in conjunction with backpropagation in differentially private optimization. This results in private learning that is as memory-efficient and almost as fast per training update as non-private learning for many of interest.
  arXiv  Detail & Related papers  (2022-12-03T05:20:15Z)
• Variance Reduced Local SGD with Lower Communication Complexity [52.44473777232414]
  We propose Variance Reduced Local SGD to further reduce the communication complexity. VRL-SGD achieves a emphlinear iteration speedup with a lower communication complexity $O(Tfrac12 Nfrac32)$ even if workers access non-identical datasets.
  arXiv  Detail & Related papers  (2019-12-30T08:15:21Z)

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.