NIGHT -- Non-Line-of-Sight Imaging from Indirect Time of Flight Data
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912035799826432 |
|---|---|
| author | Caligiuri, Matteo Simonetto, Adriano Zanuttigh, Pietro |
| author_facet | Caligiuri, Matteo Simonetto, Adriano Zanuttigh, Pietro |
| contents | The acquisition of objects outside the Line-of-Sight of cameras is a very intriguing but also extremely challenging research topic. Recent works showed the feasibility of this idea exploiting transient imaging data produced by custom direct Time of Flight sensors. In this paper, for the first time, we tackle this problem using only data from an off-the-shelf indirect Time of Flight sensor without any further hardware requirement. We introduced a Deep Learning model able to re-frame the surfaces where light bounces happen as a virtual mirror. This modeling makes the task easier to handle and also facilitates the construction of annotated training data. From the obtained data it is possible to retrieve the depth information of the hidden scene. We also provide a first-in-its-kind synthetic dataset for the task and demonstrate the feasibility of the proposed idea over it. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_19376 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | NIGHT -- Non-Line-of-Sight Imaging from Indirect Time of Flight Data Caligiuri, Matteo Simonetto, Adriano Zanuttigh, Pietro Computer Vision and Pattern Recognition Artificial Intelligence Image and Video Processing The acquisition of objects outside the Line-of-Sight of cameras is a very intriguing but also extremely challenging research topic. Recent works showed the feasibility of this idea exploiting transient imaging data produced by custom direct Time of Flight sensors. In this paper, for the first time, we tackle this problem using only data from an off-the-shelf indirect Time of Flight sensor without any further hardware requirement. We introduced a Deep Learning model able to re-frame the surfaces where light bounces happen as a virtual mirror. This modeling makes the task easier to handle and also facilitates the construction of annotated training data. From the obtained data it is possible to retrieve the depth information of the hidden scene. We also provide a first-in-its-kind synthetic dataset for the task and demonstrate the feasibility of the proposed idea over it. |
| title | NIGHT -- Non-Line-of-Sight Imaging from Indirect Time of Flight Data |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Image and Video Processing |
| url | https://arxiv.org/abs/2403.19376 |