SAGD: Boundary-Enhanced Segment Anything in 3D Gaussian via Gaussian Decomposition
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913655062265856 |
|---|---|
| author | Hu, Xu Wang, Yuxi Fan, Lue Luo, Chuanchen Fan, Junsong Lei, Zhen Li, Qing Peng, Junran Zhang, Zhaoxiang |
| author_facet | Hu, Xu Wang, Yuxi Fan, Lue Luo, Chuanchen Fan, Junsong Lei, Zhen Li, Qing Peng, Junran Zhang, Zhaoxiang |
| contents | 3D Gaussian Splatting has emerged as an alternative 3D representation for novel view synthesis, benefiting from its high-quality rendering results and real-time rendering speed. However, the 3D Gaussians learned by 3D-GS have ambiguous structures without any geometry constraints. This inherent issue in 3D-GS leads to a rough boundary when segmenting individual objects. To remedy these problems, we propose SAGD, a conceptually simple yet effective boundary-enhanced segmentation pipeline for 3D-GS to improve segmentation accuracy while preserving segmentation speed. Specifically, we introduce a Gaussian Decomposition scheme, which ingeniously utilizes the special structure of 3D Gaussian, finds out, and then decomposes the boundary Gaussians. Moreover, to achieve fast interactive 3D segmentation, we introduce a novel training-free pipeline by lifting a 2D foundation model to 3D-GS. Extensive experiments demonstrate that our approach achieves high-quality 3D segmentation without rough boundary issues, which can be easily applied to other scene editing tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_17857 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SAGD: Boundary-Enhanced Segment Anything in 3D Gaussian via Gaussian Decomposition Hu, Xu Wang, Yuxi Fan, Lue Luo, Chuanchen Fan, Junsong Lei, Zhen Li, Qing Peng, Junran Zhang, Zhaoxiang Computer Vision and Pattern Recognition 3D Gaussian Splatting has emerged as an alternative 3D representation for novel view synthesis, benefiting from its high-quality rendering results and real-time rendering speed. However, the 3D Gaussians learned by 3D-GS have ambiguous structures without any geometry constraints. This inherent issue in 3D-GS leads to a rough boundary when segmenting individual objects. To remedy these problems, we propose SAGD, a conceptually simple yet effective boundary-enhanced segmentation pipeline for 3D-GS to improve segmentation accuracy while preserving segmentation speed. Specifically, we introduce a Gaussian Decomposition scheme, which ingeniously utilizes the special structure of 3D Gaussian, finds out, and then decomposes the boundary Gaussians. Moreover, to achieve fast interactive 3D segmentation, we introduce a novel training-free pipeline by lifting a 2D foundation model to 3D-GS. Extensive experiments demonstrate that our approach achieves high-quality 3D segmentation without rough boundary issues, which can be easily applied to other scene editing tasks. |
| title | SAGD: Boundary-Enhanced Segment Anything in 3D Gaussian via Gaussian Decomposition |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2401.17857 |