SalientGS: Unified SfM-to-3DGS with Importance-Guided MCMC Gaussian Allocation

Tianyu Xiong · Rui Li · Suning Ge · Jiaqi Yang

ACM Multimedia 2026

Quality, speed, and model-size comparison for SalientGS

Abstract

Reconstructing 3D scenes from unordered images remains bottlenecked by expensive Structure-from-Motion preprocessing and frozen pose interfaces. SalientGS is a unified SfM-to-3DGS pipeline whose central contribution is importance-guided MCMC Gaussian allocation. In the released 13-scene verification, SalientGS achieves the best three-benchmark macro-average PSNR, SSIM, LPIPS, and end-to-end runtime among the compared methods, while using a fixed 1.5M-Gaussian budget.

Pipeline

SalientGS pipeline from Fisher Vector matching through first-order SfM to joint optimization

What is new

Importance-guided allocation

Persistent multi-view underfit guides birth and relocation, reallocating capacity from redundant regions.

Unified optimization

Fast first-order SfM is jointly refined with the Gaussian scene using photometric and reprojection losses.

Unordered-image front end

Fisher Vector retrieval and MST connectivity provide a sparse, reliable matching graph without exhaustive matching.

Fixed-budget efficiency

Importance guidance improves quality most when Gaussian capacity is limited, including a 1.0M-versus-1.5M comparison.

Results

MethodMip-NeRF 360 PSNRMip-NeRF 360 LPIPSDeep Blending LPIPSTanks & Temples LPIPS
3DGS-MCMC28.010.1860.2370.149
GloSplat-A28.860.1390.508*0.147
VGGT-X26.490.1770.545†0.138
SalientGS28.820.1480.1830.109

* GloSplat-A and † VGGT-X fail on the Deep Blending drjohnson scene.

Cross-benchmark macro-average: SalientGS obtains 27.65 dB PSNR, 0.876 SSIM, 0.147 LPIPS, and 10.62 minutes end-to-end. Each benchmark receives equal weight and failed scenes remain included.

Citation

@inproceedings{xiong2026salientgs,
  author    = {Tianyu Xiong and Rui Li and Suning Ge and Jiaqi Yang},
  title     = {SalientGS: Unified SfM-to-3DGS with Importance-Guided MCMC Gaussian Allocation},
  booktitle = {Proceedings of the 34th ACM International Conference on Multimedia},
  year      = {2026}
}