Neural Underwater Scene Representation

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

Research output: Contribution to conferenceConference paperpeer-review

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 languageEnglish
Publication statusPublished - 20 Jun 2024
EventThe IEEE / CVF Computer Vision and Pattern Recognition Conference, CVPR 2024 - Seattle Convention Center, Seattle, United States
Duration: 17 Jun 202421 Jun 2024
https://cvpr.thecvf.com/ (conference website)
https://cvpr2023.thecvf.com/virtual/2023/calendar (Link to conference schedule)
https://media.eventhosts.cc/Conferences/CVPR2024/CVPR_main_conf_2024.pdf (Link to conference booklet)

Conference

ConferenceThe IEEE / CVF Computer Vision and Pattern Recognition Conference, CVPR 2024
Abbreviated titleCVPR 2024
Country/TerritoryUnited States
CitySeattle
Period17/06/2421/06/24
Internet address

Fingerprint

Dive into the research topics of 'Neural Underwater Scene Representation'. Together they form a unique fingerprint.

Cite this