IQGS: Instance Query-based Gaussian Segmentation
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (6) · 4194-4202
DOI: 10.1609/aaai.v40i6.42415 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Yichao Gao und 4 weiteren Autor:innen.
Abstract (Originalsprache)
In recent years, Gaussian scene representations have achieved a series of promising results in 3D reconstruction. Compared to the previous 3DGS paradigm, the latest reconstruction approach 2DGS can achieve more accurate geometric representation using fewer Gaussian points. Accordingly, developing a panoramic segmentation algorithm suitable for 2DGS-reconstructed scenes is of significant importance. However, existing segmentation methods are primarily designed for 3DGS. They either fail to account for all objects in complex segmentation scenes or suffer from significant performance degradation when applied to 2D Gaussian scenes. Moreover, these methods consistently exhibit poor cross-dataset generalization. To address these issues, we propose IQGS, a segmentation framework applicable to 2DGS representations. Specifically, IQGS employs per-instance query and relaxed object-level supervision instead of strict pixel-level ID supervision, effectively mitigating the segmentation performance degradation that occurs when applied to 2DGS. At the same time, by learning features independent of specific object ID assignments, IQGS enhances its ability to generalize across diverse datasets. Our method achieves impressive panoramic segmentation results across multiple datasets, with an average mIoU of 66.6%, surpassing the state-of-the-art method Gaussian Grouping, which achieves 57.17%.
Zitieren
APA
Gao, Y., Liu, X., Ma, Y., Zhang, Y., & Dai, F. (2026). IQGS: Instance Query-based Gaussian Segmentation. Proceedings of the AAAI Conference on Artificial Intelligence, 40(6), 4194-4202. https://doi.org/10.1609/aaai.v40i6.42415
Vancouver
Gao Y, Liu X, Ma Y, Zhang Y, Dai F. IQGS: Instance Query-based Gaussian Segmentation. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(6):4194-4202. doi:10.1609/aaai.v40i6.42415
BibTeX
@article{Gao2026,
author = {Gao, Yichao and Liu, Xinyuan and Ma, Yike and Zhang, Yucheng and Dai, Feng},
title = {IQGS: Instance Query-based Gaussian Segmentation},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {6},
pages = {4194--4202},
doi = {10.1609/aaai.v40i6.42415}
}
EUVIMED