Occam's LGS: An Efficient Approach for Language Gaussian Splatting

TL;DR

This paper introduces Occam's LGS, a simplified and highly efficient method for language-augmented Gaussian Splatting in 3D scene representation, achieving state-of-the-art results with significantly reduced computational costs.

Contribution

It proposes a probabilistic formulation and a streamlined multi-view feature aggregation technique that eliminates complex pipelines, greatly enhancing efficiency and ease of scene manipulation.

Findings

Achieves two orders of magnitude speed-up over previous methods.

Maintains high-quality 3D scene reconstruction and rendering.

Enables effective open-set semantic tasks with less computational effort.

Abstract

TL;DR: Gaussian Splatting is a widely adopted approach for 3D scene representation, offering efficient, high-quality reconstruction and rendering. A key reason for its success is the simplicity of representing scenes with sets of Gaussians, making it interpretable and adaptable. To enhance understanding beyond visual representation, recent approaches extend Gaussian Splatting with semantic vision-language features, enabling open-set tasks. Typically, these language features are aggregated from multiple 2D views, however, existing methods rely on cumbersome techniques, resulting in high computational costs and longer training times. In this work, we show that the complicated pipelines for language 3D Gaussian Splatting are simply unnecessary. Instead, we follow a probabilistic formulation of Language Gaussian Splatting and apply Occam's razor to the task at hand, leading to a highly efficient weighted multi-view feature aggregation technique. Doing so offers us state-of-the-art results with a speed-up of two orders of magnitude without any compression, allowing for easy scene manipulation. Project Page: https://insait-institute.github.io/OccamLGS/