Relative Illumination Fields: Learning Medium and Light Independent Underwater Scenes
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_ | 1866915240950628352 |
|---|---|
| author | She, Mengkun Seegräber, Felix Nakath, David Schöntag, Patricia Köser, Kevin |
| author_facet | She, Mengkun Seegräber, Felix Nakath, David Schöntag, Patricia Köser, Kevin |
| contents | We address the challenge of constructing a consistent and photorealistic Neural Radiance Field in inhomogeneously illuminated, scattering environments with unknown, co-moving light sources. While most existing works on underwater scene representation focus on a static homogeneous illumination, limited attention has been paid to scenarios such as when a robot explores water deeper than a few tens of meters, where sunlight becomes insufficient. To address this, we propose a novel illumination field locally attached to the camera, enabling the capture of uneven lighting effects within the viewing frustum. We combine this with a volumetric medium representation to an overall method that effectively handles interaction between dynamic illumination field and static scattering medium. Evaluation results demonstrate the effectiveness and flexibility of our approach. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_10024 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Relative Illumination Fields: Learning Medium and Light Independent Underwater Scenes She, Mengkun Seegräber, Felix Nakath, David Schöntag, Patricia Köser, Kevin Computer Vision and Pattern Recognition We address the challenge of constructing a consistent and photorealistic Neural Radiance Field in inhomogeneously illuminated, scattering environments with unknown, co-moving light sources. While most existing works on underwater scene representation focus on a static homogeneous illumination, limited attention has been paid to scenarios such as when a robot explores water deeper than a few tens of meters, where sunlight becomes insufficient. To address this, we propose a novel illumination field locally attached to the camera, enabling the capture of uneven lighting effects within the viewing frustum. We combine this with a volumetric medium representation to an overall method that effectively handles interaction between dynamic illumination field and static scattering medium. Evaluation results demonstrate the effectiveness and flexibility of our approach. |
| title | Relative Illumination Fields: Learning Medium and Light Independent Underwater Scenes |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.10024 |