ToF-Splatting: Dense SLAM using Sparse Time-of-Flight Depth and Multi-Frame Integration
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_ | 1866916703503384576 |
|---|---|
| author | Conti, Andrea Poggi, Matteo Cambareri, Valerio Oswald, Martin R. Mattoccia, Stefano |
| author_facet | Conti, Andrea Poggi, Matteo Cambareri, Valerio Oswald, Martin R. Mattoccia, Stefano |
| contents | Time-of-Flight (ToF) sensors provide efficient active depth sensing at relatively low power budgets; among such designs, only very sparse measurements from low-resolution sensors are considered to meet the increasingly limited power constraints of mobile and AR/VR devices. However, such extreme sparsity levels limit the seamless usage of ToF depth in SLAM. In this work, we propose ToF-Splatting, the first 3D Gaussian Splatting-based SLAM pipeline tailored for using effectively very sparse ToF input data. Our approach improves upon the state of the art by introducing a multi-frame integration module, which produces dense depth maps by merging cues from extremely sparse ToF depth, monocular color, and multi-view geometry. Extensive experiments on both synthetic and real sparse ToF datasets demonstrate the viability of our approach, as it achieves state-of-the-art tracking and mapping performances on reference datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_16545 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ToF-Splatting: Dense SLAM using Sparse Time-of-Flight Depth and Multi-Frame Integration Conti, Andrea Poggi, Matteo Cambareri, Valerio Oswald, Martin R. Mattoccia, Stefano Computer Vision and Pattern Recognition Time-of-Flight (ToF) sensors provide efficient active depth sensing at relatively low power budgets; among such designs, only very sparse measurements from low-resolution sensors are considered to meet the increasingly limited power constraints of mobile and AR/VR devices. However, such extreme sparsity levels limit the seamless usage of ToF depth in SLAM. In this work, we propose ToF-Splatting, the first 3D Gaussian Splatting-based SLAM pipeline tailored for using effectively very sparse ToF input data. Our approach improves upon the state of the art by introducing a multi-frame integration module, which produces dense depth maps by merging cues from extremely sparse ToF depth, monocular color, and multi-view geometry. Extensive experiments on both synthetic and real sparse ToF datasets demonstrate the viability of our approach, as it achieves state-of-the-art tracking and mapping performances on reference datasets. |
| title | ToF-Splatting: Dense SLAM using Sparse Time-of-Flight Depth and Multi-Frame Integration |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.16545 |