Training-Free Hierarchical Scene Understanding for Gaussian Splatting with Superpoint Graphs
Open Access
- 27 October 2025
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 3673-3682
Abstract
No abstract availableAll Related Versions
Funding Information
- National Science Fund for Distinguished Young Scholars (62025603)
- National Natural Science Foundation of China (U21B2037, U22B2051, U23A20383, U21A20472, 62176222, 62176223, 62176226, 62072386, 62072387, 62072389, 62002305, 62272401)
- Natural Science Foundation of Fujian Province of China (2021J06003, 2022J06001)
This publication has 30 references indexed in Scilit:
- Language Embedded 3D Gaussians for Open-Vocabulary Scene Understanding2024
- Open3DIS: Open-Vocabulary 3D Instance Segmentation with 2D Mask Guidance2024
- Mip-Splatting: Alias-Free 3D Gaussian Splatting2024
- TeMO: Towards Text-Driven 3D Stylization for Multi-Object Meshes2024
- SAI3D: Segment any Instance in 3D Scenes2024
- SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering2024
- Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields2022
- Point Cloud Oversegmentation With Graph-Structured Deep Metric Learning2019
- Large-Scale Point Cloud Semantic Segmentation with Superpoint Graphs2018
- ScanNet: Richly-Annotated 3D Reconstructions of Indoor Scenes2017