GAGS: Granularity-Aware Feature Distillation for Language Gaussian Splatting
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (10) · 8376-8384
DOI: 10.1609/aaai.v40i10.37787 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Yuning Peng und 5 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref).
Abstract (Originalsprache)
3D open-vocabulary scene understanding, which accurately perceives complex semantic properties of objects in space, has gained significant attention in recent years. In this paper, we propose GAGS, a framework that distills 2D CLIP features into 3D Gaussian splatting, enabling open-vocabulary queries for renderings on arbitrary viewpoints. The main challenge of distilling 2D features for 3D fields lies in the multiview inconsistency of extracted 2D features, which provides unstable supervision for the 3D feature field. GAGS addresses this challenge with two novel strategies. First, GAGS associates the prompt point density of SAM with the camera distances to scene objects, which significantly improves the multiview consistency of segmentation results. Second, GAGS further decodes a granularity factor to guide the distillation process and this granularity factor can be learned in a unsupervised manner to only select the multiview consistent 2D features in the distillation process. Experimental results on two datasets show that GAGS improves visual grounding accuracy by an average of 10.9% and semantic segmentation accuracy by an average of 7.0%, with an inference speed 2× faster than baseline methods.
Zitieren
APA
Peng, Y., Wang, H., Liu, Y., Wen, C., Dong, Z., & Yang, B. (2026). GAGS: Granularity-Aware Feature Distillation for Language Gaussian Splatting. Proceedings of the AAAI Conference on Artificial Intelligence, 40(10), 8376-8384. https://doi.org/10.1609/aaai.v40i10.37787
Vancouver
Peng Y, Wang H, Liu Y, Wen C, Dong Z, Yang B. GAGS: Granularity-Aware Feature Distillation for Language Gaussian Splatting. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(10):8376-8384. doi:10.1609/aaai.v40i10.37787
BibTeX
@article{Peng2026,
author = {Peng, Yuning and Wang, Haiping and Liu, Yuan and Wen, Chenglu and Dong, Zhen and Yang, Bisheng},
title = {GAGS: Granularity-Aware Feature Distillation for Language Gaussian Splatting},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {10},
pages = {8376--8384},
doi = {10.1609/aaai.v40i10.37787}
}
EUVIMED