Semantic Gaussians: Open-Vocabulary Scene Understanding with 3D Gaussian Splatting

TL;DR

Semantic Gaussians introduces a novel 3D scene understanding method that distills knowledge from 2D pre-trained models into 3D Gaussian representations, enabling versatile applications with superior performance.

Contribution

The paper proposes a new approach that maps 2D semantic features into 3D Gaussians without additional training, enhancing open-vocabulary scene understanding.

Findings

Superior segmentation performance on ScanNet and LERF datasets

Effective in object part and instance segmentation

Supports diverse downstream tasks with qualitative improvements

Abstract

Open-vocabulary 3D scene understanding presents a significant challenge in computer vision, with wide-ranging applications in embodied agents and augmented reality systems. Existing methods adopt neurel rendering methods as 3D representations and jointly optimize color and semantic features to achieve rendering and scene understanding simultaneously. In this paper, we introduce Semantic Gaussians, a novel open-vocabulary scene understanding approach based on 3D Gaussian Splatting. Our key idea is to distill knowledge from 2D pre-trained models to 3D Gaussians. Unlike existing methods, we design a versatile projection approach that maps various 2D semantic features from pre-trained image encoders into a novel semantic component of 3D Gaussians, which is based on spatial relationship and need no additional training. We further build a 3D semantic network that directly predicts the semantic component from raw 3D Gaussians for fast inference. The quantitative results on ScanNet segmentation and LERF object localization demonstates the superior performance of our method. Additionally, we explore several applications of Semantic Gaussians including object part segmentation, instance segmentation, scene editing, and spatiotemporal segmentation with better qualitative results over 2D and 3D baselines, highlighting its versatility and effectiveness on supporting diverse downstream tasks.