Unbounded-GS: Extending 3D Gaussian Splatting With Hybrid Representation for Unbounded Large-Scale Scene Reconstruction

Modeling large-scale scenes from multi-view images is challenging due to the trade-off dilemma between visual quality and computational cost. Existing NeRF-based methods have made advancements in neural implicit representation through volumetric ray-marching, but still struggle to deal with cubicall...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE robotics and automation letters 2024-12, Vol.9 (12), p.11529-11536
Hauptverfasser:	Li, Wanzhang, Yin, Fukun, Liu, Wen, Yang, Yiying, Chen, Xin, Jiang, Biao, Yu, Gang, Fan, Jiayuan
Format:	Artikel
Sprache:	eng
Schlagworte:	3D reconstruction Cameras Computational modeling Covariance matrices Deep learning for visual perception Encoding Image color analysis Neural radiance field Rendering (computer graphics) Solid modeling Three-dimensional displays Training view synthesis visual learning
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!