PointSplat: Efficient Geometry-Driven Pruning and Transformer Refinement for 3D Gaussian Splatting

TL;DR

PointSplat introduces a geometry-driven pruning and transformer refinement framework for 3D Gaussian Splatting, reducing memory usage while maintaining high-quality scene rendering without scene-specific optimization.

Contribution

It presents a novel 3D geometry-based pruning method and a dual-branch encoder for efficient, high-quality 3D scene rendering.

Findings

Achieves competitive rendering quality across datasets

Reduces memory and storage demands significantly

Operates without scene-specific optimization

Abstract

3D Gaussian Splatting (3DGS) has recently unlocked real-time, high-fidelity novel view synthesis by representing scenes using explicit 3D primitives. However, traditional methods often require millions of Gaussians to capture complex scenes, leading to significant memory and storage demands. Recent approaches have addressed this issue through pruning and per-scene fine-tuning of Gaussian parameters, thereby reducing the model size while maintaining visual quality. These strategies typically rely on 2D images to compute important scores followed by scene-specific optimization. In this work, we introduce PointSplat, 3D geometry-driven prune-and-refine framework that bridges previously disjoint directions of gaussian pruning and transformer refinement. Our method includes two key components: (1) an efficient geometry-driven strategy that ranks Gaussians based solely on their 3D attributes, removing reliance on 2D images during pruning stage, and (2) a dual-branch encoder that separates, re-weights geometric and appearance to avoid feature imbalance. Extensive experiments on ScanNet++ and Replica across varying sparsity levels demonstrate that PointSplat consistently achieves competitive rendering quality and superior efficiency without additional per-scene optimization.