Guardado en:
| Autores principales: | , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2604.03309 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914444840271872 |
|---|---|
| author | You, Jingbin Li, Zehao Jiang, Hao Ma, Xinzhu Gao, Shuqin Zhao, Honglong Zheng, Congcong Mao, Tianlu Dai, Feng Zhang, Yucheng Wang, Zhaoqi |
| author_facet | You, Jingbin Li, Zehao Jiang, Hao Ma, Xinzhu Gao, Shuqin Zhao, Honglong Zheng, Congcong Mao, Tianlu Dai, Feng Zhang, Yucheng Wang, Zhaoqi |
| contents | 3D Gaussian Splatting (3DGS) has emerged as a real-time, differentiable representation for neural scene understanding. However, existing 3DGS-based methods struggle to represent hierarchical 3D semantic structures and capture whole-part relationships in complex scenes. Moreover, dense pairwise comparisons and inconsistent hierarchical labels from 2D priors hinder feature learning, resulting in suboptimal segmentation. To address these limitations, we introduce TreeGaussian, a tree-guided cascaded contrastive learning framework that explicitly models hierarchical semantic relationships and reduces redundancy in contrastive supervision. By constructing a multi-level object tree, TreeGaussian enables structured learning across object-part hierarchies. In addition, we propose a two-stage cascaded contrastive learning strategy that progressively refines feature representations from global to local, mitigating saturation and stabilizing training. A Consistent Segmentation Detection (CSD) mechanism and a graph-based denoising module are further introduced to align segmentation modes across views while suppressing unstable Gaussian points, enhancing segmentation consistency and quality. Extensive experiments, including open-vocabulary 3D object selection, 3D point cloud understanding, and ablation studies, demonstrate the effectiveness and robustness of our approach. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_03309 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | TreeGaussian: Tree-Guided Cascaded Contrastive Learning for Hierarchical Consistent 3D Gaussian Scene Segmentation and Understanding You, Jingbin Li, Zehao Jiang, Hao Ma, Xinzhu Gao, Shuqin Zhao, Honglong Zheng, Congcong Mao, Tianlu Dai, Feng Zhang, Yucheng Wang, Zhaoqi Computer Vision and Pattern Recognition Artificial Intelligence 3D Gaussian Splatting (3DGS) has emerged as a real-time, differentiable representation for neural scene understanding. However, existing 3DGS-based methods struggle to represent hierarchical 3D semantic structures and capture whole-part relationships in complex scenes. Moreover, dense pairwise comparisons and inconsistent hierarchical labels from 2D priors hinder feature learning, resulting in suboptimal segmentation. To address these limitations, we introduce TreeGaussian, a tree-guided cascaded contrastive learning framework that explicitly models hierarchical semantic relationships and reduces redundancy in contrastive supervision. By constructing a multi-level object tree, TreeGaussian enables structured learning across object-part hierarchies. In addition, we propose a two-stage cascaded contrastive learning strategy that progressively refines feature representations from global to local, mitigating saturation and stabilizing training. A Consistent Segmentation Detection (CSD) mechanism and a graph-based denoising module are further introduced to align segmentation modes across views while suppressing unstable Gaussian points, enhancing segmentation consistency and quality. Extensive experiments, including open-vocabulary 3D object selection, 3D point cloud understanding, and ablation studies, demonstrate the effectiveness and robustness of our approach. |
| title | TreeGaussian: Tree-Guided Cascaded Contrastive Learning for Hierarchical Consistent 3D Gaussian Scene Segmentation and Understanding |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2604.03309 |