Neural Underwater Scene Representation

Yunkai Tang; Chengxuan Zhu; Renjie Wan; Chao Xu; Boxin Shi

doi:10.1109/CVPR52733.2024.01119

Neural Underwater Scene Representation

Yunkai Tang, Chengxuan Zhu, Renjie Wan^*, Chao Xu, Boxin Shi^*

^*Corresponding author for this work

Department of Computer Science

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

8 Citations (Scopus)

Abstract

Among the numerous efforts towards digitally recovering the physical world, Neural Radiance Fields (NeRFs) have proved effective in most cases. However, underwater scene introduces unique challenges due to the absorbing water medium, the local change in lighting and the dynamic contents in the scene. We aim at developing a neural underwater scene representation for these challenges, modeling the complex process of attenuation, unstable in-scattering and moving objects during light transport. The proposed method can reconstruct the scenes from both established datasets and in-the-wild videos with outstanding fidelity.

Original language	English
Title of host publication	Proceedings of 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2024
Editors	Cristina Ceballos
Publisher	IEEE
Pages	11780-11789
Number of pages	10
ISBN (Electronic)	9798350353006
ISBN (Print)	9798350353013
DOIs	https://doi.org/10.1109/CVPR52733.2024.01119
Publication status	Published - 16 Jun 2024
Event	2024 37th IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2024 - Seattle Convention Center, Seattle, United States Duration: 17 Jun 2024 → 21 Jun 2024 https://cvpr.thecvf.com/Conferences/2024 (Conference website) https://cvpr.thecvf.com/virtual/2024 (Conference website) https://cvpr.thecvf.com/virtual/2024/calendar (conference schedule) https://media.eventhosts.cc/Conferences/CVPR2024/CVPR_main_conf_2024.pdf (Conference program) https://openaccess.thecvf.com/CVPR2024 (Conference proceedings) https://ieeexplore.ieee.org/xpl/conhome/10654794/proceeding (Conference proceedings)

Publication series

Name	Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
Publisher	IEEE
ISSN (Print)	1063-6919
ISSN (Electronic)	2575-7075

Conference

Conference	2024 37th IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2024
Abbreviated title	CVPR 2024
Country/Territory	United States
City	Seattle
Period	17/06/24 → 21/06/24
Internet address	https://cvpr.thecvf.com/Conferences/2024 (Conference website) https://cvpr.thecvf.com/virtual/2024 (Conference website) https://cvpr.thecvf.com/virtual/2024/calendar (conference schedule) https://media.eventhosts.cc/Conferences/CVPR2024/CVPR_main_conf_2024.pdf (Conference program) https://openaccess.thecvf.com/CVPR2024 (Conference proceedings) https://ieeexplore.ieee.org/xpl/conhome/10654794/proceeding (Conference proceedings)

User-Defined Keywords

implicit neural representation
nerf
neural radiance fields
underwater

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/CVPR52733.2024.01119

https://openaccess.thecvf.com/content/CVPR2024/papers/Tang_Neural_Underwater_Scene_Representation_CVPR_2024_paper.pdf

Cite this

@inproceedings{38a0877b6cde4cd0a357852c80cbba5f,

title = "Neural Underwater Scene Representation",

abstract = "Among the numerous efforts towards digitally recovering the physical world, Neural Radiance Fields (NeRFs) have proved effective in most cases. However, underwater scene introduces unique challenges due to the absorbing water medium, the local change in lighting and the dynamic contents in the scene. We aim at developing a neural underwater scene representation for these challenges, modeling the complex process of attenuation, unstable in-scattering and moving objects during light transport. The proposed method can reconstruct the scenes from both established datasets and in-the-wild videos with outstanding fidelity.",

keywords = "implicit neural representation, nerf, neural radiance fields, underwater",

author = "Yunkai Tang and Chengxuan Zhu and Renjie Wan and Chao Xu and Boxin Shi",

note = "Funding Information: This work is supported by National Natural Science Foundation of China under Grant No. 62136001, 62088102, 62276007. Renjie Wan is supported by the National Natural Science Foundation of China under Grant No. 62302415, Guangdong Basic and Applied Basic Research Foundation under Grant No. 2022A1515110692, 2024A1515012822, and the Blue Sky Research Fund of HKBU under Grant No. BSRF/21-22/16. Publisher copyright: {\textcopyright}2024 IEEE; 2024 37th IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2024, CVPR 2024 ; Conference date: 17-06-2024 Through 21-06-2024",

year = "2024",

month = jun,

day = "16",

doi = "10.1109/CVPR52733.2024.01119",

language = "English",

isbn = "9798350353013",

series = "Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition",

publisher = "IEEE",

pages = "11780--11789",

editor = "Cristina Ceballos",

booktitle = "Proceedings of 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2024",

address = "United States",

url = "https://cvpr.thecvf.com/Conferences/2024, https://cvpr.thecvf.com/virtual/2024, https://cvpr.thecvf.com/virtual/2024/calendar, https://media.eventhosts.cc/Conferences/CVPR2024/CVPR_main_conf_2024.pdf, https://openaccess.thecvf.com/CVPR2024, https://ieeexplore.ieee.org/xpl/conhome/10654794/proceeding",

}

Tang, Y, Zhu, C, Wan, R, Xu, C & Shi, B 2024, Neural Underwater Scene Representation. in C Ceballos (ed.), Proceedings of 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2024. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, IEEE, pp. 11780-11789, 2024 37th IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2024, Seattle, Washington, United States, 17/06/24. https://doi.org/10.1109/CVPR52733.2024.01119

Neural Underwater Scene Representation. / Tang, Yunkai; Zhu, Chengxuan; Wan, Renjie et al.
Proceedings of 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2024. ed. / Cristina Ceballos. IEEE, 2024. p. 11780-11789 (Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition).

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

TY - GEN

T1 - Neural Underwater Scene Representation

AU - Tang, Yunkai

AU - Zhu, Chengxuan

AU - Wan, Renjie

AU - Xu, Chao

AU - Shi, Boxin

N1 - Funding Information: This work is supported by National Natural Science Foundation of China under Grant No. 62136001, 62088102, 62276007. Renjie Wan is supported by the National Natural Science Foundation of China under Grant No. 62302415, Guangdong Basic and Applied Basic Research Foundation under Grant No. 2022A1515110692, 2024A1515012822, and the Blue Sky Research Fund of HKBU under Grant No. BSRF/21-22/16. Publisher copyright: ©2024 IEEE

PY - 2024/6/16

Y1 - 2024/6/16

N2 - Among the numerous efforts towards digitally recovering the physical world, Neural Radiance Fields (NeRFs) have proved effective in most cases. However, underwater scene introduces unique challenges due to the absorbing water medium, the local change in lighting and the dynamic contents in the scene. We aim at developing a neural underwater scene representation for these challenges, modeling the complex process of attenuation, unstable in-scattering and moving objects during light transport. The proposed method can reconstruct the scenes from both established datasets and in-the-wild videos with outstanding fidelity.

AB - Among the numerous efforts towards digitally recovering the physical world, Neural Radiance Fields (NeRFs) have proved effective in most cases. However, underwater scene introduces unique challenges due to the absorbing water medium, the local change in lighting and the dynamic contents in the scene. We aim at developing a neural underwater scene representation for these challenges, modeling the complex process of attenuation, unstable in-scattering and moving objects during light transport. The proposed method can reconstruct the scenes from both established datasets and in-the-wild videos with outstanding fidelity.

KW - implicit neural representation

KW - nerf

KW - neural radiance fields

KW - underwater

UR - https://www.youtube.com/watch?v=qaWLwv8VxlI

UR - https://cvpr2023.thecvf.com/virtual/2024/poster/29691

UR - http://www.scopus.com/inward/record.url?scp=85200259513&partnerID=8YFLogxK

UR - https://openaccess.thecvf.com/content/CVPR2024/html/Tang_Neural_Underwater_Scene_Representation_CVPR_2024_paper.html

U2 - 10.1109/CVPR52733.2024.01119

DO - 10.1109/CVPR52733.2024.01119

M3 - Conference proceeding

SN - 9798350353013

T3 - Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

SP - 11780

EP - 11789

BT - Proceedings of 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2024

A2 - Ceballos, Cristina

PB - IEEE

T2 - 2024 37th IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2024

Y2 - 17 June 2024 through 21 June 2024

ER -

Neural Underwater Scene Representation

Abstract

Publication series

Conference

User-Defined Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this