GSplatVNM: Point-of-View Synthesis for Visual Navigation Models Using Gaussian Splatting
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911077951864832 |
|---|---|
| author | Honda, Kohei Ishita, Takeshi Yoshimura, Yasuhiro Yonetani, Ryo |
| author_facet | Honda, Kohei Ishita, Takeshi Yoshimura, Yasuhiro Yonetani, Ryo |
| contents | This paper presents a novel approach to image-goal navigation by integrating 3D Gaussian Splatting (3DGS) with Visual Navigation Models (VNMs), a method we refer to as GSplatVNM. VNMs offer a promising paradigm for image-goal navigation by guiding a robot through a sequence of point-of-view images without requiring metrical localization or environment-specific training. However, constructing a dense and traversable sequence of target viewpoints from start to goal remains a central challenge, particularly when the available image database is sparse. To address these challenges, we propose a 3DGS-based viewpoint synthesis framework for VNMs that synthesizes intermediate viewpoints to seamlessly bridge gaps in sparse data while significantly reducing storage overhead. Experimental results in a photorealistic simulator demonstrate that our approach not only enhances navigation efficiency but also exhibits robustness under varying levels of image database sparsity. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_05152 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GSplatVNM: Point-of-View Synthesis for Visual Navigation Models Using Gaussian Splatting Honda, Kohei Ishita, Takeshi Yoshimura, Yasuhiro Yonetani, Ryo Robotics This paper presents a novel approach to image-goal navigation by integrating 3D Gaussian Splatting (3DGS) with Visual Navigation Models (VNMs), a method we refer to as GSplatVNM. VNMs offer a promising paradigm for image-goal navigation by guiding a robot through a sequence of point-of-view images without requiring metrical localization or environment-specific training. However, constructing a dense and traversable sequence of target viewpoints from start to goal remains a central challenge, particularly when the available image database is sparse. To address these challenges, we propose a 3DGS-based viewpoint synthesis framework for VNMs that synthesizes intermediate viewpoints to seamlessly bridge gaps in sparse data while significantly reducing storage overhead. Experimental results in a photorealistic simulator demonstrate that our approach not only enhances navigation efficiency but also exhibits robustness under varying levels of image database sparsity. |
| title | GSplatVNM: Point-of-View Synthesis for Visual Navigation Models Using Gaussian Splatting |
| topic | Robotics |
| url | https://arxiv.org/abs/2503.05152 |