Underwater scene characterization method based on neural radiation field

The invention provides an underwater scene characterization method based on a neural radiation field, which is realized by designing corresponding modules in a neural network, and comprises a hybrid progressive sampling module, a scene parameter estimation module and a hybrid volume rendering module...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: TANG YUNKAI, SHI BAIXIN, XU CHAO, ZHU CHENGXUAN
Format: Patent
Sprache:chi ; eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The invention provides an underwater scene characterization method based on a neural radiation field, which is realized by designing corresponding modules in a neural network, and comprises a hybrid progressive sampling module, a scene parameter estimation module and a hybrid volume rendering module, high-quality static reconstruction of an underwater scene is realized for an underwater data set without a time sequence, and the underwater scene characterization method based on the neural radiation field is realized. The three-dimensional reconstruction performance on the data set is improved; for an underwater data set with time sequence information, high-quality dynamic reconstruction of an underwater scene is realized, the motion trail of underwater creatures and real-time change of illumination are recovered, and the application range of the algorithm is expanded; the rendering speed is greatly superior to that of other existing underwater scene three-dimensional reconstruction methods, and the performance