paper-with-me

Papers

OpenSplat3D: Open-Vocabulary 3D Instance Segmentation using Gaussian Splatting

2025-06-09 · Jens Piekenbrinck, Christian Schmidt, Alexander Hermans, Narunas Vaskevicius, Timm Linder, Bastian Leibe

3D Gaussian Splatting (3DGS) has emerged as a powerful representation for neural scene reconstruction, offering high-quality novel view synthesis while maintaining computational efficiency. In this paper, we extend the capabilities of 3DGS beyond pure scene representation by introducing an approach for open-vocabulary 3D instance segmentation without requiring manual labeling, termed OpenSplat3D. Our method leverages feature-splatting techniques to associate semantic information with individual Gaussians, enabling fine-grained scene understanding. We incorporate Segment Anything Model instance masks with a contrastive loss formulation as guidance for the instance features to achieve accurate instance-level segmentation. Furthermore, we utilize language embeddings of a vision-language model, allowing for flexible, text-driven instance identification. This combination enables our system to identify and segment arbitrary objects in 3D scenes based on natural language descriptions. We show results on LERF-mask and LERF-OVS as well as the full ScanNet++ validation set, demonstrating the effectiveness of our approach.

📄 PDF Abstract BibTeX arXiv:2506.07697

Code (0)

등록된 구현이 없습니다.

Tasks

3DGS3D Instance SegmentationComputational EfficiencyFeature SplattingInstance SegmentationLanguage ModelingLanguage ModellingNovel View Synthesisopen vocabulary 3d instance segmentationScene UnderstandingSemantic Segmentation

Similar Papers 제목 키워드 기반

Relation-Centric Open-Vocabulary 3D Gaussian Segmentation

2026-07-01 · Eunsung Cha, Hyunjoon Lee, Jaesik Park arxiv

Open-vocabulary 3D Gaussian segmentation is challenging because it requires language understanding for diverse queries and accurate separation of Gaussians along object boundaries. Prior approaches either embed language …

GLS: Geometry-aware 3D Language Gaussian Splatting

2024-11-27 · Jiaxiong Qiu, Liu Liu, Zhizhong Su, Tianwei Lin

Recently, 3D Gaussian Splatting (3DGS) has achieved significant performance on indoor surface reconstruction and open-vocabulary segmentation. This paper presents GLS, a unified framework of surface reconstruction and op…

3DGSSegmentationSurface Reconstruction

PanoGS: Gaussian-based Panoptic Segmentation for 3D Open Vocabulary Scene Understanding

2025-03-23 · CVPR 2025 1 · Hongjia Zhai, Hai Li, Zhenzhe Li, Xiaokun Pan 외

Recently, 3D Gaussian Splatting (3DGS) has shown encouraging performance for open vocabulary scene understanding tasks. However, previous methods cannot distinguish 3D instance-level information, which usually predicts a…

3DGSDecoderGraph ClusteringPanoptic Segmentation+1

OVGaussian: Generalizable 3D Gaussian Segmentation with Open Vocabularies

2024-12-31 · Runnan Chen, Xiangyu Sun, Zhaoqing Wang, Youquan Liu 외

Open-vocabulary scene understanding using 3D Gaussian (3DGS) representations has garnered considerable attention. However, existing methods mostly lift knowledge from large 2D vision models into 3DGS on a scene-by-scene …

3DGS3D Semantic SegmentationOpen Vocabulary Semantic SegmentationOpen-Vocabulary Semantic Segmentation+2

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

2025-10-21 · Tianyu Huang, Runnan Chen, Dongting Hu, Fengming Huang 외 arxiv

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 scen…

Scene UnderstandingAutonomous Driving