Leveraging 2D-VLM for Label-Free 3D Segmentation in Large-Scale Outdoor Scene Understanding
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917184522944512 |
|---|---|
| author | Nishimura, Toshihiko Abe, Hirofumi Murasaki, Kazuhiko Yoshida, Taiga Tanida, Ryuichi |
| author_facet | Nishimura, Toshihiko Abe, Hirofumi Murasaki, Kazuhiko Yoshida, Taiga Tanida, Ryuichi |
| contents | This paper presents a novel 3D semantic segmentation method for large-scale point cloud data that does not require annotated 3D training data or paired RGB images. The proposed approach projects 3D point clouds onto 2D images using virtual cameras and performs semantic segmentation via a foundation 2D model guided by natural language prompts. 3D segmentation is achieved by aggregating predictions from multiple viewpoints through weighted voting. Our method outperforms existing training-free approaches and achieves segmentation accuracy comparable to supervised methods. Moreover, it supports open-vocabulary recognition, enabling users to detect objects using arbitrary text queries, thus overcoming the limitations of traditional supervised approaches. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_02029 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Leveraging 2D-VLM for Label-Free 3D Segmentation in Large-Scale Outdoor Scene Understanding Nishimura, Toshihiko Abe, Hirofumi Murasaki, Kazuhiko Yoshida, Taiga Tanida, Ryuichi Computer Vision and Pattern Recognition This paper presents a novel 3D semantic segmentation method for large-scale point cloud data that does not require annotated 3D training data or paired RGB images. The proposed approach projects 3D point clouds onto 2D images using virtual cameras and performs semantic segmentation via a foundation 2D model guided by natural language prompts. 3D segmentation is achieved by aggregating predictions from multiple viewpoints through weighted voting. Our method outperforms existing training-free approaches and achieves segmentation accuracy comparable to supervised methods. Moreover, it supports open-vocabulary recognition, enabling users to detect objects using arbitrary text queries, thus overcoming the limitations of traditional supervised approaches. |
| title | Leveraging 2D-VLM for Label-Free 3D Segmentation in Large-Scale Outdoor Scene Understanding |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2601.02029 |