Metropolis-Hastings Sampling for 3D Gaussian Reconstruction
By: Hyunjin Kim, Haebeom Jung, Jaesik Park
Potential Business Impact:
Makes 3D pictures look better with fewer dots.
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. Traditional 3DGS methods heavily rely on heuristic-based density-control mechanisms (e.g., cloning, splitting, and pruning), which can lead to redundant computations or the 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, enhancing computational efficiency while matching or modestly surpassing the view-synthesis quality of state-of-the-art models.
Similar Papers
Improving Adaptive Density Control for 3D Gaussian Splatting
CV and Pattern Recognition
Makes 3D pictures look better and train faster.
Unposed 3DGS Reconstruction with Probabilistic Procrustes Mapping
CV and Pattern Recognition
Creates detailed 3D worlds from many photos.
Diffusion-Guided Gaussian Splatting for Large-Scale Unconstrained 3D Reconstruction and Novel View Synthesis
CV and Pattern Recognition
Creates realistic 3D worlds from few pictures.