SAM2Scene: SAM Knows How to Segment 3D Instances
Open Access
- 9 November 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 15311-15319
Abstract
No abstract availableFunding Information
- Beijing Natural Science Foundation (L257003)
- National Natural Science Foundation of China (62402033)
This publication has 26 references indexed in Scilit:
- EmbodiedScan: A Holistic Multi-Modal 3D Perception Suite Towards Embodied AI2024
- Alpha-CLIP: A CLIP Model Focusing on Wherever you Want2024
- Open3DIS: Open-Vocabulary 3D Instance Segmentation with 2D Mask Guidance2024
- SAI3D: Segment any Instance in 3D Scenes2024
- ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution2023
- OpenScene: 3D Scene Understanding with Open Vocabularies2023
- Language-Grounded Indoor 3D Semantic Segmentation in the Wild2022
- PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation2020
- ScanNet: Richly-Annotated 3D Reconstructions of Indoor Scenes2017
- Efficient Graph-Based Image SegmentationInternational Journal of Computer Vision, 2004