TY - GEN
T1 - LabelGS
T2 - 8th Chinese Conference on Pattern Recognition and Computer Vision, PRCV 2025
AU - Zhang, Yupeng
AU - Zheng, Dezhi
AU - Lu, Ping
AU - Zhang, Han
AU - Wang, Lei
AU - Xiang, Liping
AU - Luo, Cheng
AU - Deng, Kaijun
AU - Fu, Xiaowen
AU - Shen, Linlin
AU - Wang, Jinbao
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026.
PY - 2026
Y1 - 2026
N2 - 3D Gaussian Splatting (3DGS) has emerged as a novel explicit representation for 3D scenes, offering both high-fidelity reconstruction and efficient rendering. However, 3DGS lacks 3D segmentation ability, which limits its applicability in tasks that require scene understanding. The identification and isolation of specific object components is crucial. To address this limitation, we propose Label-aware 3D Gaussian Splatting (LabelGS), a method that augments the Gaussian representation with object label. LabelGS introduces cross-view consistent semantic masks for 3D Gaussians and employs a novel Occlusion Analysis Model to avoid overfitting occlusion during optimization, Main Gaussian Labeling model to lift 2D semantic prior to 3D Gaussian and Gaussian Projection Filter to avoid Gaussian label conflict. Our approach achieves effective decoupling of Gaussian representations and refines the 3DGS optimization process through a random region sampling strategy, significantly improving efficiency. Extensive experiments demonstrate that LabelGS outperforms previous state-of-the-art methods, including Feature-3DGS, in the 3D scene segmentation task. Notably, LabelGS achieves a remarkable 22× speedup in training compared to Feature-3DGS, at a resolution of 1440×1080. Our code will be at https://github.com/garrisonz/LabelGS
AB - 3D Gaussian Splatting (3DGS) has emerged as a novel explicit representation for 3D scenes, offering both high-fidelity reconstruction and efficient rendering. However, 3DGS lacks 3D segmentation ability, which limits its applicability in tasks that require scene understanding. The identification and isolation of specific object components is crucial. To address this limitation, we propose Label-aware 3D Gaussian Splatting (LabelGS), a method that augments the Gaussian representation with object label. LabelGS introduces cross-view consistent semantic masks for 3D Gaussians and employs a novel Occlusion Analysis Model to avoid overfitting occlusion during optimization, Main Gaussian Labeling model to lift 2D semantic prior to 3D Gaussian and Gaussian Projection Filter to avoid Gaussian label conflict. Our approach achieves effective decoupling of Gaussian representations and refines the 3DGS optimization process through a random region sampling strategy, significantly improving efficiency. Extensive experiments demonstrate that LabelGS outperforms previous state-of-the-art methods, including Feature-3DGS, in the 3D scene segmentation task. Notably, LabelGS achieves a remarkable 22× speedup in training compared to Feature-3DGS, at a resolution of 1440×1080. Our code will be at https://github.com/garrisonz/LabelGS
KW - 3D Gaussian Splatting
KW - 3D Segmentation
KW - Gaussian Annotation
UR - https://www.scopus.com/pages/publications/105028381504
U2 - 10.1007/978-981-95-5737-0_4
DO - 10.1007/978-981-95-5737-0_4
M3 - Conference contribution
AN - SCOPUS:105028381504
SN - 9789819557363
T3 - Lecture Notes in Computer Science
SP - 47
EP - 61
BT - Pattern Recognition and Computer Vision - 8th Chinese Conference, PRCV 2025, Proceedings
A2 - Kittler, Josef
A2 - Xiong, Hongkai
A2 - Lin, Weiyao
A2 - Yang, Jian
A2 - Chen, Xilin
A2 - Lu, Jiwen
A2 - Yu, Jingyi
A2 - Zheng, Weishi
PB - Springer Science and Business Media Deutschland GmbH
Y2 - 15 October 2025 through 18 October 2025
ER -