Zero-Shot Visual Grounding in 3D Gaussians via View Retrieval
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912847719563264 |
|---|---|
| author | Liao, Liwei Li, Xufeng Zheng, Xiaoyun Liu, Boning Gao, Feng Wang, Ronggang |
| author_facet | Liao, Liwei Li, Xufeng Zheng, Xiaoyun Liu, Boning Gao, Feng Wang, Ronggang |
| contents | 3D Visual Grounding (3DVG) aims to locate objects in 3D scenes based on text prompts, which is essential for applications such as robotics. However, existing 3DVG methods encounter two main challenges: first, they struggle to handle the implicit representation of spatial textures in 3D Gaussian Splatting (3DGS), making per-scene training indispensable; second, they typically require larges amounts of labeled data for effective training. To this end, we propose \underline{G}rounding via \underline{V}iew \underline{R}etrieval (GVR), a novel zero-shot visual grounding framework for 3DGS to transform 3DVG as a 2D retrieval task that leverages object-level view retrieval to collect grounding clues from multiple views, which not only avoids the costly process of 3D annotation, but also eliminates the need for per-scene training. Extensive experiments demonstrate that our method achieves state-of-the-art visual grounding performance while avoiding per-scene training, providing a solid foundation for zero-shot 3DVG research. Video demos can be found in https://github.com/leviome/GVR_demos. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_15871 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Zero-Shot Visual Grounding in 3D Gaussians via View Retrieval Liao, Liwei Li, Xufeng Zheng, Xiaoyun Liu, Boning Gao, Feng Wang, Ronggang Computer Vision and Pattern Recognition Multimedia 3D Visual Grounding (3DVG) aims to locate objects in 3D scenes based on text prompts, which is essential for applications such as robotics. However, existing 3DVG methods encounter two main challenges: first, they struggle to handle the implicit representation of spatial textures in 3D Gaussian Splatting (3DGS), making per-scene training indispensable; second, they typically require larges amounts of labeled data for effective training. To this end, we propose \underline{G}rounding via \underline{V}iew \underline{R}etrieval (GVR), a novel zero-shot visual grounding framework for 3DGS to transform 3DVG as a 2D retrieval task that leverages object-level view retrieval to collect grounding clues from multiple views, which not only avoids the costly process of 3D annotation, but also eliminates the need for per-scene training. Extensive experiments demonstrate that our method achieves state-of-the-art visual grounding performance while avoiding per-scene training, providing a solid foundation for zero-shot 3DVG research. Video demos can be found in https://github.com/leviome/GVR_demos. |
| title | Zero-Shot Visual Grounding in 3D Gaussians via View Retrieval |
| topic | Computer Vision and Pattern Recognition Multimedia |
| url | https://arxiv.org/abs/2509.15871 |