Efficient Scene Modeling via Structure-Aware and Region-Prioritized 3D Gaussians

TL;DR

This paper introduces Mini-Splatting2, a novel 3D scene modeling framework that leverages structure-aware distribution and region-prioritized optimization to improve efficiency and quality in 3D Gaussian reconstruction.

Contribution

Mini-Splatting2 presents a geometry-regulated paradigm for 3D Gaussian modeling, enhancing spatial regularity and convergence speed while reducing the number of primitives needed.

Findings

Achieves up to 4× fewer Gaussians

Faster optimization by 3×

Maintains state-of-the-art visual quality

Abstract

Reconstructing 3D scenes with high fidelity and efficiency remains a central pursuit in computer vision and graphics. Recent advances in 3D Gaussian Splatting (3DGS) enable photorealistic rendering with Gaussian primitives, yet the modeling process remains governed predominantly by photometric supervision. This reliance often leads to irregular spatial distribution and indiscriminate primitive adjustments that largely ignore underlying geometric context. In this work, we rethink Gaussian modeling from a geometric standpoint and introduce Mini-Splatting2, an efficient scene modeling framework that couples structure-aware distribution and region-prioritized optimization, driving 3DGS into a geometry-regulated paradigm. The structure-aware distribution enforces spatial regularity through structured reorganization and representation sparsity, ensuring balanced structural coverage for compact organization. The region-prioritized optimization improves training discrimination through geometric saliency and computational selectivity, fostering appropriate structural emergence for fast convergence. These mechanisms alleviate the long-standing tension among representation compactness, convergence acceleration, and rendering fidelity. Extensive experiments demonstrate that Mini-Splatting2 achieves up to 4$\times$ fewer Gaussians and 3$\times$ faster optimization while maintaining state-of-the-art visual quality, paving the way towards structured and efficient 3D Gaussian modeling.