City-on-Web: Real-time Neural Rendering of Large-scale Scenes on the Web

arXiv:2312.16457v2 Announce Type: replace
Abstract: Existing neural radiance field-based methods can achieve real-time rendering of small scenes on the web platform. However, extending these methods to large-scale scenes still poses significant challenges due to limited resources in computation, memory, and bandwidth. In this paper, we propose City-on-Web, the first method for real-time rendering of large-scale scenes on the web. We propose a block-based volume rendering method to guarantee 3D consistency and correct occlusion between blocks, and introduce a Level-of-Detail strategy …

abstract arxiv bandwidth challenges city computation cs.cv cs.gr however memory neural radiance field neural rendering paper platform real-time rendering resources scale small type web