AD-GS: Alternating Densification for Sparse-Input 3D Gaussian Splatting

• URL: http://arxiv.org/abs/2509.11003v2
• Date: Mon, 22 Sep 2025 12:25:56 GMT
• Title: AD-GS: Alternating Densification for Sparse-Input 3D Gaussian Splatting
• Authors: Gurutva Patle, Nilay Girgaonkar, Nagabhushan Somraj, Rajiv Soundararajan,
• Abstract summary: 3D Gaussian Splatting (3DGS) has shown impressive results in real-time novel view synthesis.<n>We find that a key contributing factor is uncontrolled densification, where adding primitives rapidly without guidance can harm geometry and cause artifacts.<n>We propose AD-GS, a novel alternating densification framework that interleaves high and low densification phases.
• Score: 6.696418686121452
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 3D Gaussian Splatting (3DGS) has shown impressive results in real-time novel view synthesis. However, it often struggles under sparse-view settings, producing undesirable artifacts such as floaters, inaccurate geometry, and overfitting due to limited observations. We find that a key contributing factor is uncontrolled densification, where adding Gaussian primitives rapidly without guidance can harm geometry and cause artifacts. We propose AD-GS, a novel alternating densification framework that interleaves high and low densification phases. During high densification, the model densifies aggressively, followed by photometric loss based training to capture fine-grained scene details. Low densification then primarily involves aggressive opacity pruning of Gaussians followed by regularizing their geometry through pseudo-view consistency and edge-aware depth smoothness. This alternating approach helps reduce overfitting by carefully controlling model capacity growth while progressively refining the scene representation. Extensive experiments on challenging datasets demonstrate that AD-GS significantly improves rendering quality and geometric consistency compared to existing methods. The source code for our model can be found on our project page: https://gurutvapatle.github.io/publications/2025/ADGS.html .

Related papers

• Visibility-Aware Densification for 3D Gaussian Splatting in Dynamic Urban Scenes [7.253732091582086]
  VAD-GS is a 3DGS framework tailored for geometry recovery in challenging urban scenes.<n>Our method identifies unreliable geometry structures via voxel-based visibility reasoning.<n>It selects informative supporting views through diversity-aware view selection, and recovers missing structures via patch matching-based stereo reconstruction.
  arXiv  Detail & Related papers  (2025-10-10T13:22:12Z)
• OracleGS: Grounding Generative Priors for Sparse-View Gaussian Splatting [78.70702961852119]
  OracleGS reconciles generative completeness with regressive fidelity for sparse view Gaussian Splatting.<n>Our approach conditions the powerful generative prior on multi-view geometric evidence, filtering hallucinatory artifacts while preserving plausible completions in under-constrained regions.
  arXiv  Detail & Related papers  (2025-09-27T11:19:32Z)
• Improving Densification in 3D Gaussian Splatting for High-Fidelity Rendering [3.6379656024631215]
  We present a comprehensive improvement to the densification pipeline of 3DGS.<n>Specifically, we propose an Edge-Aware Score to effectively select candidate Gaussians for splitting.<n>We also introduce a Long-Axis Split strategy that reduces geometric distortions introduced by clone and split operations.
  arXiv  Detail & Related papers  (2025-08-17T10:13:21Z)
• DET-GS: Depth- and Edge-Aware Regularization for High-Fidelity 3D Gaussian Splatting [5.759434800012218]
  3D Gaussian Splatting (3DGS) represents a significant advancement in the field of efficient and high-fidelity novel view synthesis.<n>Existing methods often rely on non-local depth regularization, which fails to capture fine-grained structures.<n>We propose DET-GS, a unified depth and edge-aware regularization framework for 3D Gaussian Splatting.
  arXiv  Detail & Related papers  (2025-08-06T05:37:26Z)
• RobustSplat: Decoupling Densification and Dynamics for Transient-Free 3DGS [79.15416002879239]
  3D Gaussian Splatting has gained significant attention for its real-time, photo-realistic rendering in novel-view synthesis and 3D modeling.<n>Existing methods struggle with accurately modeling scenes affected by transient objects, leading to artifacts in the rendered images.<n>We propose RobustSplat, a robust solution based on two critical designs.
  arXiv  Detail & Related papers  (2025-06-03T11:13:48Z)
• 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)
• ResGS: Residual Densification of 3D Gaussian for Efficient Detail Recovery [11.706262924395768]
  We introduce a novel densification operation, residual split, which adds a downscaled Gaussian as a residual.<n>Our approach is capable of adaptively retrieving details and complementing missing geometry.
  arXiv  Detail & Related papers  (2024-12-10T13:19:27Z)
• Pushing Rendering Boundaries: Hard Gaussian Splatting [72.28941128988292]
  3D Gaussian Splatting (3DGS) has demonstrated impressive Novel View Synthesis (NVS) results in a real-time rendering manner.<n>We propose Hard Gaussian Splatting, dubbed HGS, which considers multi-view significant positional gradients and rendering errors to grow hard Gaussians.<n>Our method achieves state-of-the-art rendering quality while maintaining real-time efficiency.
  arXiv  Detail & Related papers  (2024-12-06T07:42:47Z)
• CityGaussianV2: Efficient and Geometrically Accurate Reconstruction for Large-Scale Scenes [53.107474952492396]
  CityGaussianV2 is a novel approach for large-scale scene reconstruction.<n>We implement a decomposed-gradient-based densification and depth regression technique to eliminate blurry artifacts and accelerate convergence.<n>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)
• 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)
• AbsGS: Recovering Fine Details for 3D Gaussian Splatting [10.458776364195796]
  3D Gaussian Splatting (3D-GS) technique couples 3D primitives with differentiable Gaussianization to achieve high-quality novel view results. However, 3D-GS frequently suffers from over-reconstruction issue in intricate scenes containing high-frequency details, leading to blurry rendered images. We present a comprehensive analysis of the cause of aforementioned artifacts, namely gradient collision. Our strategy efficiently identifies large Gaussians in over-reconstructed regions, and recovers fine details by splitting.
  arXiv  Detail & Related papers  (2024-04-16T11:44:12Z)
• 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)

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.