Metropolis-Hastings Sampling for 3D Gaussian Reconstruction

Hyunjin Kim, Haebeom Jung, Jaesik Park

Keywords: 3D Gaussian Splatting, Metropolis-Hastings Sampling

TL;DR: A Metropolis–Hastings driven adaptive sampling framework for 3D Gaussian Splatting that unifies densification and pruning to achieve more efficient, high-quality real-time scene reconstructions with fewer Gaussians.

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.

Primary Area: Applications (e.g., vision, language, speech and audio, Creative AI)

Submission Number: 9768