paper-with-me

홈 › Papers

OpenGS-Fusion: Open-Vocabulary Dense Mapping with Hybrid 3D Gaussian Splatting for Refined Object-Level Understanding

2025-08-02 · Dianyi Yang, Xihan Wang, Yu Gao, Shiyang Liu, Bohan Ren, Yufeng Yue, Yi Yang arxiv

Recent advancements in 3D scene understanding have made significant strides in enabling interaction with scenes using open-vocabulary queries, particularly for VR/AR and robotic applications. Nevertheless, existing methods are hindered by rigid offline pipelines and the inability to provide precise 3D object-level understanding given open-ended queries. In this paper, we present OpenGS-Fusion, an innovative open-vocabulary dense mapping framework that improves semantic modeling and refines object-level understanding. OpenGS-Fusion combines 3D Gaussian representation with a Truncated Signed Distance Field to facilitate lossless fusion of semantic features on-the-fly. Furthermore, we introduce a novel multimodal language-guided approach named MLLM-Assisted Adaptive Thresholding, which refines the segmentation of 3D objects by adaptively adjusting similarity thresholds, achieving an improvement 17\% in 3D mIoU compared to the fixed threshold strategy. Extensive experiments demonstrate that our method outperforms existing methods in 3D object understanding and scene reconstruction quality, as well as showcasing its effectiveness in language-guided scene interaction. The code is available at https://young-bit.github.io/opengs-fusion.github.io/ .

📄 PDF Abstract BibTeX arXiv:2508.01150

Code (0)

등록된 구현이 없습니다.

Tasks

Scene Understanding

Similar Papers 제목 키워드 기반

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

2025-03-03 · Dianyi Yang, Yu Gao, Xihan Wang, Yufeng Yue 외

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 …

Scene UnderstandingSemantic SLAM

FUS3DMaps: Scalable and Accurate Open-Vocabulary Semantic Mapping by 3D Fusion of Voxel- and Instance-Level Layers

2026-05-05 · Timon Homberger, Finn Lukas Busch, Jesús Gerardo Ortega Peimbert, Quantao Yang 외 arxiv

Open-vocabulary semantic mapping enables robots to spatially ground previously unseen concepts without requiring predefined class sets. Current training-free methods commonly rely on multi-view fusion of semantic embeddi…

3D Semantic Segmentation

RGB-Only Gaussian Splatting SLAM for Unbounded Outdoor Scenes

2025-02-21 · Sicheng Yu, Chong Cheng, Yifan Zhou, Xiaojun Yang 외

3D Gaussian Splatting (3DGS) has become a popular solution in SLAM, as it can produce high-fidelity novel views. However, previous GS-based methods primarily target indoor scenes and rely on RGB-D sensors or pre-trained …

3DGSCamera Pose EstimationDepth EstimationNovel View Synthesis+2

OVI-MAP:Open-Vocabulary Instance-Semantic Mapping

2026-03-27 · Zilong Deng, Federico Tombari, Marc Pollefeys, Johanna Wald 외 arxiv

Incremental open-vocabulary 3D instance-semantic mapping is essential for autonomous agents operating in complex everyday environments. However, it remains challenging due to the need for robust instance segmentation, re…

Instance Segmentation

OpenGSL: A Comprehensive Benchmark for Graph Structure Learning

2023-06-17 · NeurIPS 2023 11 · Zhiyao Zhou, Sheng Zhou, Bochao Mao, Xuanyi Zhou 외

Graph Neural Networks (GNNs) have emerged as the de facto standard for representation learning on graphs, owing to their ability to effectively integrate graph topology and node attributes. However, the inherent suboptim…

Graph structure learningRepresentation Learning