Sem-SLAM: Semantic-Integrated SLAM Approach for 3D Reconstruction

Under the upsurge of research on the integration of Simultaneous Localization and Mapping (SLAM) and neural implicit representation, existing methods exhibit obvious limitations in terms of environmental semantic parsing and scene understanding capabilities. In response to this, this paper proposes...

Full description

Saved in:
Bibliographic Details
Main Authors: Shuqi Liu, Yufeng Zhuang, Chenxu Zhang, Qifei Li, Jiayu Hou
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/14/7881
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849406788722491392
author Shuqi Liu
Yufeng Zhuang
Chenxu Zhang
Qifei Li
Jiayu Hou
author_facet Shuqi Liu
Yufeng Zhuang
Chenxu Zhang
Qifei Li
Jiayu Hou
author_sort Shuqi Liu
collection DOAJ
description Under the upsurge of research on the integration of Simultaneous Localization and Mapping (SLAM) and neural implicit representation, existing methods exhibit obvious limitations in terms of environmental semantic parsing and scene understanding capabilities. In response to this, this paper proposes a SLAM system that integrates a full attention mechanism and a multi-scale information extractor. This system constructs a more accurate 3D environmental model by fusing semantic, shape, and geometric orientation features. Meanwhile, to deeply excavate the semantic information in images, a pre-trained frozen 2D segmentation algorithm is employed to extract semantic features, providing a powerful support for 3D environmental reconstruction. Furthermore, a multi-layer perceptron and interpolation techniques are utilized to extract multi-scale features, distinguishing information at different scales. This enables the effective decoding of semantic, RGB, and Truncated Signed Distance Field (TSDF) values from the fused features, achieving high-quality information rendering. Experimental results demonstrate that this method significantly outperforms the baseline-based methods in terms of mapping and tracking accuracy on the Replica and ScanNet datasets. It also shows superior performance in semantic segmentation and real-time semantic mapping tasks, offering a new direction for the development of SLAM technology.
format Article
id doaj-art-69b360ef2e9640c2b7d5a5b98a1a7c5c
institution Kabale University
issn 2076-3417
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-69b360ef2e9640c2b7d5a5b98a1a7c5c2025-08-20T03:36:15ZengMDPI AGApplied Sciences2076-34172025-07-011514788110.3390/app15147881Sem-SLAM: Semantic-Integrated SLAM Approach for 3D ReconstructionShuqi Liu0Yufeng Zhuang1Chenxu Zhang2Qifei Li3Jiayu Hou4Key Laboratory of IoT Monitoring and Early Warning, Ministry of Emergency Management, School of Intelligent Engieering and Automation, Beijing University of Posts and Telecommunications, Beijing 100876, ChinaKey Laboratory of IoT Monitoring and Early Warning, Ministry of Emergency Management, School of Intelligent Engieering and Automation, Beijing University of Posts and Telecommunications, Beijing 100876, ChinaKey Laboratory of IoT Monitoring and Early Warning, Ministry of Emergency Management, School of Intelligent Engieering and Automation, Beijing University of Posts and Telecommunications, Beijing 100876, ChinaKey Laboratory of IoT Monitoring and Early Warning, Ministry of Emergency Management, School of Intelligent Engieering and Automation, Beijing University of Posts and Telecommunications, Beijing 100876, ChinaKey Laboratory of IoT Monitoring and Early Warning, Ministry of Emergency Management, School of Intelligent Engieering and Automation, Beijing University of Posts and Telecommunications, Beijing 100876, ChinaUnder the upsurge of research on the integration of Simultaneous Localization and Mapping (SLAM) and neural implicit representation, existing methods exhibit obvious limitations in terms of environmental semantic parsing and scene understanding capabilities. In response to this, this paper proposes a SLAM system that integrates a full attention mechanism and a multi-scale information extractor. This system constructs a more accurate 3D environmental model by fusing semantic, shape, and geometric orientation features. Meanwhile, to deeply excavate the semantic information in images, a pre-trained frozen 2D segmentation algorithm is employed to extract semantic features, providing a powerful support for 3D environmental reconstruction. Furthermore, a multi-layer perceptron and interpolation techniques are utilized to extract multi-scale features, distinguishing information at different scales. This enables the effective decoding of semantic, RGB, and Truncated Signed Distance Field (TSDF) values from the fused features, achieving high-quality information rendering. Experimental results demonstrate that this method significantly outperforms the baseline-based methods in terms of mapping and tracking accuracy on the Replica and ScanNet datasets. It also shows superior performance in semantic segmentation and real-time semantic mapping tasks, offering a new direction for the development of SLAM technology.https://www.mdpi.com/2076-3417/15/14/7881artificialintelligenceintelligent industrial systemsSLAMemergency responseneural implicit representation
spellingShingle Shuqi Liu
Yufeng Zhuang
Chenxu Zhang
Qifei Li
Jiayu Hou
Sem-SLAM: Semantic-Integrated SLAM Approach for 3D Reconstruction
Applied Sciences
artificialintelligence
intelligent industrial systems
SLAM
emergency response
neural implicit representation
title Sem-SLAM: Semantic-Integrated SLAM Approach for 3D Reconstruction
title_full Sem-SLAM: Semantic-Integrated SLAM Approach for 3D Reconstruction
title_fullStr Sem-SLAM: Semantic-Integrated SLAM Approach for 3D Reconstruction
title_full_unstemmed Sem-SLAM: Semantic-Integrated SLAM Approach for 3D Reconstruction
title_short Sem-SLAM: Semantic-Integrated SLAM Approach for 3D Reconstruction
title_sort sem slam semantic integrated slam approach for 3d reconstruction
topic artificialintelligence
intelligent industrial systems
SLAM
emergency response
neural implicit representation
url https://www.mdpi.com/2076-3417/15/14/7881
work_keys_str_mv AT shuqiliu semslamsemanticintegratedslamapproachfor3dreconstruction
AT yufengzhuang semslamsemanticintegratedslamapproachfor3dreconstruction
AT chenxuzhang semslamsemanticintegratedslamapproachfor3dreconstruction
AT qifeili semslamsemanticintegratedslamapproachfor3dreconstruction
AT jiayuhou semslamsemanticintegratedslamapproachfor3dreconstruction