Lune

NeurIPS2025Top-tier venue

Metropolis-Hastings Sampling for 3D Gaussian Reconstruction

Hyunjin Kim, Haebeom Jung, Jaesik Park

Abstract

We propose an adaptive sampling framework for 3D Gaussian Splatting (3DGS) that leverages comprehensive multi-view photometric error signals within a unified Metropolis-Hastings approach. Vanilla 3DGS heavily relies on heuristic-based density-control mechanisms (e.g., cloning, splitting, and pruning), which can lead to redundant computations or premature removal of beneficial Gaussians. Our framework overcomes these limitations by reformulating densification and pruning as a probabilistic sampling process, dynamically inserting and relocating Gaussians based on aggregated multi-view errors and opacity scores. Guided by Bayesian acceptance tests derived from these error-based importance scores, our method substantially reduces reliance on heuristics, offers greater flexibility, and adaptively infers Gaussian distributions without requiring predefined scene complexity. Experiments on benchmark datasets, including Mip-NeRF360, Tanks and Temples and Deep Blending, show that our approach reduces the number of Gaussians needed, achieving faster convergence while matching or modestly surpassing the view-synthesis quality of state-of-the-art models. Our project page is available at https://hjhyunjinkim.github.io/MH-3DGS.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

2 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • 3D Gaussian Splatting for Real-Time Radiance Field Rendering cites Instant neural graphics primitives with a multiresolution hash encoding
  • 3D Gaussian Splatting for Real-Time Radiance Field Rendering cites Plenoxels: Radiance Fields without Neural Networks
  • CoverPruneGS: Coverage-Preserving Structured Pruning for Hierarchical 3D Gaussian Splatting from Sparse-View Monocular Videos cites 3D Gaussian Splatting for Real-Time Radiance Field Rendering
  • CoverPruneGS: Coverage-Preserving Structured Pruning for Hierarchical 3D Gaussian Splatting from Sparse-View Monocular Videos cites Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers2

  1. Graphical X Splatting (GraphiXS): A Graphical Model for 4D Gaussian Splatting under UncertaintyDoga Yilmaz, Jialin Zhu, Deshan Gong, He WangSIGGRAPH 2026
  2. CoverPruneGS: Coverage-Preserving Structured Pruning for Hierarchical 3D Gaussian Splatting from Sparse-View Monocular VideosYang Xiao, Guoan Xu, Guxue Gao, Qiang Wu et al.ICML 2026

Builds on38

  1. 3D Gaussian Splatting for Real-Time Radiance Field RenderingBernhard Kerbl, Georgios Kopanas, Thomas Leimkühler, George DrettakisSIGGRAPH 2023 · 5,687 citations
  2. Instant neural graphics primitives with a multiresolution hash encodingThomas Müller, Alex Evans, Christoph Schied, Alexander KellerSIGGRAPH 2022 · 4,089 citations
  3. Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance FieldsJonathan T. Barron, Ben Mildenhall, Dor Verbin, Pratul P. Srinivasan et al.CVPR 2022 · 1,603 citations
  4. Nerfies: Deformable Neural Radiance FieldsKeunhong Park, Utkarsh Sinha, Jonathan T. Barron, Sofien Bouaziz et al.ICCV 2021 · 1,442 citations
  5. Plenoxels: Radiance Fields without Neural NetworksSara Fridovich-Keil, Alex Yu, Matthew Tancik, Qinhong Chen et al.CVPR 2022 · 1,237 citations

Related papers

  1. Pushing Rendering Boundaries: Hard Gaussian SplattingQingshan Xu, Jiequan Cui, Xuanyu Yi, Yuxuan Wang et al.AAAI 2026
  2. FastGS: Training 3D Gaussian Splatting in 100 SecondsShiwei Ren, Tianci Wen, Yongchun Fang, Biao LuCVPR 2026 · 55 citations
  3. Eulerian Gaussian Splatting using Hashed Probability PyramidsMia Gaia Polansky, George Kopanas, Stephan J. Garbin, Todd E. Zickler et al.CVPR 2026
  4. PCGS: Deblurring 3D Gaussian Splatting with Patch ComparisonYilong Li, Bo Pang, Zhongtao Wang, Mai Su et al.ICML 2026
  5. VAD-GS: Visibility-Aware Densification for 3D Gaussian Splatting in Dynamic Urban ScenesYikang Zhang, Rui FanCVPR 2026
Dusk over the sea between two cliffs drawn in fine vertical lines