SkipGS: Post-Densification Backward Skipping for Efficient 3DGS Training

• URL: http://arxiv.org/abs/2603.08997v1
• Date: Mon, 09 Mar 2026 22:32:52 GMT
• Title: SkipGS: Post-Densification Backward Skipping for Efficient 3DGS Training
• Abstract summary: 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.
• Score: 40.28141759111142
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 3D Gaussian Splatting (3DGS) achieves real-time novel-view synthesis by optimizing millions of anisotropic Gaussians, yet its training remains expensive, with the backward pass dominating runtime in the post-densification refinement phase. We observe substantial update redundancy in this phase: many sampled views have near-plateaued losses and provide diminishing gradient benefits, but standard training still runs full backpropagation. We propose SkipGS with a novel view-adaptive backward gating mechanism for efficient post-densification training. SkipGS always performs the forward pass to update per-view loss statistics, and selectively skips backward passes when the sampled view's loss is consistent with its recent per-view baseline, while enforcing a minimum backward budget for stable optimization. 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, with comparable reconstruction quality. Because it only changes when to backpropagate -- without modifying the renderer, representation, or loss -- SkipGS is plug-and-play and compatible with other complementary efficiency strategies for additive speedups.

Related papers

• 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)
• ForeSplat: Optimization-Aware Foresight for Feed-Forward 3D Gaussian Splatting [65.02700555625749]
  ForeSplat is an optimization-aware training framework for feed-forward 3DGS models.<n>ForeSplat substantially reduces the capacity pressure on the feed-forward model.<n>It bridges the gap between amortized prediction and per-scene optimization.
  arXiv  Detail & Related papers  (2026-05-21T05:38:47Z)
• GIFSplat: Generative Prior-Guided Iterative Feed-Forward 3D Gaussian Splatting from Sparse Views [44.787835922271135]
  GIFSplat is a purely feed-forward iterative refinement framework for 3D Gaussian refineting from sparse unposed views.<n>It consistently outperforms state-of-the-art feed-forward baselines across DL3DV, RealEstate10K, and DTU.<n>It maintains second-scale inference time without requiring camera poses or any test-time gradient optimization.
  arXiv  Detail & Related papers  (2026-02-26T03:25:18Z)
• GSta: Efficient Training Scheme with Siestaed Gaussians for Monocular 3D Scene Reconstruction [4.865050337780373]
  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.
  arXiv  Detail & Related papers  (2025-04-09T09:17:56Z)
• FreeSplat++: Generalizable 3D Gaussian Splatting for Efficient Indoor Scene Reconstruction [50.534213038479926]
  FreeSplat++ is an alternative approach to large-scale indoor whole-scene reconstruction.<n>Our method with depth-regularized per-scene fine-tuning demonstrates substantial improvements in reconstruction accuracy and a notable reduction in training time.
  arXiv  Detail & Related papers  (2025-03-29T06:22:08Z)
• Gaussian On-the-Fly Splatting: A Progressive Framework for Robust Near Real-Time 3DGS Optimization [8.422116335889163]
  3D Gaussian Splatting (3DGS) achieves high-fidelity rendering with fast real-time performance.<n>Existing methods rely on offline training after full Structure-from-Motion (SfM) processing.<n>We introduce On-the-Fly GS, a progressive framework enabling near real-time 3DGS optimization during image capture.
  arXiv  Detail & Related papers  (2025-03-17T11:47:58Z)
• 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)
• 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)

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.