# OpenGS-SLAM: Open-Set Dense Semantic SLAM with 3D Gaussian Splatting for Object-Level Scene Understanding

Source: [OpenGS-SLAM: Open-Set Dense Semantic SLAM with 3D Gaussian Splatting for Object-Level Scene Understanding](<https://www.sota2.com/research/paper/68fa77381e209131cea71c10>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T04:12:54.213Z

Authors: Dianyi Yang, Yu Gao, Xihan Wang, Yufeng Yue, Yi Yang, Mengyin Fu

Published: 2025-03-03T15:23:21.000Z

## Abstract

Recent advancements in 3D Gaussian Splatting have significantly improved the efficiency and quality of dense semantic SLAM. However, previous methods are generally constrained by limited-category pre-trained classifiers and implicit semantic representation, which hinder their performance in open-set scenarios and restrict 3D object-level scene understanding. To address these issues, we propose OpenGS-SLAM, an innovative framework that utilizes 3D Gaussian representation to perform dense semantic SLAM in open-set environments. Our system integrates explicit semantic labels derived from 2D foundational models into the 3D Gaussian framework, facilitating robust 3D object-level scene understanding. We introduce Gaussian Voting Splatting to enable fast 2D label map rendering and scene updating. Additionally, we propose a Confidence-based 2D Label Consensus method to ensure consistent labeling across multiple views. Furthermore, we employ a Segmentation Counter Pruning strategy to improve the accuracy of semantic scene representation. Extensive experiments on both synthetic and real-world datasets demonstrate the effectiveness of our method in scene understanding, tracking, and mapping, achieving 10 times faster semantic rendering and 2 times lower storage costs compared to existing methods. Project page: https://young-bit.github.io/opengs-github.github.io/.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Semantic Segmentation on Replica](<https://www.sota2.com/research/sota/semantic-segmentation-on-replica.md>): Semantic segmentation; Replica; Avg Accuracy: 73.11.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2503.01646>)

[PDF](<https://arxiv.org/pdf/2503.01646.pdf>)
