OpenInsGaussian: Open-vocabulary Instance Gaussian Segmentation with Context-aware Cross-view Fusion

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Huang, Tianyu, Chen, Runnan, Hu, Dongting, Huang, Fengming, Gong, Mingming, Liu, Tongliang
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915566231486464
author Huang, Tianyu
Chen, Runnan
Hu, Dongting
Huang, Fengming
Gong, Mingming
Liu, Tongliang
author_facet Huang, Tianyu
Chen, Runnan
Hu, Dongting
Huang, Fengming
Gong, Mingming
Liu, Tongliang
contents Understanding 3D scenes is pivotal for autonomous driving, robotics, and augmented reality. Recent semantic Gaussian Splatting approaches leverage large-scale 2D vision models to project 2D semantic features onto 3D scenes. However, they suffer from two major limitations: (1) insufficient contextual cues for individual masks during preprocessing and (2) inconsistencies and missing details when fusing multi-view features from these 2D models. In this paper, we introduce \textbf{OpenInsGaussian}, an \textbf{Open}-vocabulary \textbf{Ins}tance \textbf{Gaussian} segmentation framework with Context-aware Cross-view Fusion. Our method consists of two modules: Context-Aware Feature Extraction, which augments each mask with rich semantic context, and Attention-Driven Feature Aggregation, which selectively fuses multi-view features to mitigate alignment errors and incompleteness. Through extensive experiments on benchmark datasets, OpenInsGaussian achieves state-of-the-art results in open-vocabulary 3D Gaussian segmentation, outperforming existing baselines by a large margin. These findings underscore the robustness and generality of our proposed approach, marking a significant step forward in 3D scene understanding and its practical deployment across diverse real-world scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2510_18253
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle OpenInsGaussian: Open-vocabulary Instance Gaussian Segmentation with Context-aware Cross-view Fusion
Huang, Tianyu
Chen, Runnan
Hu, Dongting
Huang, Fengming
Gong, Mingming
Liu, Tongliang
Computer Vision and Pattern Recognition
Understanding 3D scenes is pivotal for autonomous driving, robotics, and augmented reality. Recent semantic Gaussian Splatting approaches leverage large-scale 2D vision models to project 2D semantic features onto 3D scenes. However, they suffer from two major limitations: (1) insufficient contextual cues for individual masks during preprocessing and (2) inconsistencies and missing details when fusing multi-view features from these 2D models. In this paper, we introduce \textbf{OpenInsGaussian}, an \textbf{Open}-vocabulary \textbf{Ins}tance \textbf{Gaussian} segmentation framework with Context-aware Cross-view Fusion. Our method consists of two modules: Context-Aware Feature Extraction, which augments each mask with rich semantic context, and Attention-Driven Feature Aggregation, which selectively fuses multi-view features to mitigate alignment errors and incompleteness. Through extensive experiments on benchmark datasets, OpenInsGaussian achieves state-of-the-art results in open-vocabulary 3D Gaussian segmentation, outperforming existing baselines by a large margin. These findings underscore the robustness and generality of our proposed approach, marking a significant step forward in 3D scene understanding and its practical deployment across diverse real-world scenarios.
title OpenInsGaussian: Open-vocabulary Instance Gaussian Segmentation with Context-aware Cross-view Fusion
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.18253