City-on-Web: Real-Time Neural Rendering of Large-Scale Scenes on the Web
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 accommodate the independent resource characteristics of web-based rendering, and introduce a Level-of-Detail strategy combined with dynamic loading/unloading of resources to significantly reduce memory demands. Our system achieves real-time rendering of large-scale scenes at 32FPS with RTX 3060 GPU on the web and maintains quality comparable to the current state-of-the-art novel view synthesis methods. Project page: https://ustc3dv.github.io/City-on-Web/
Cite
Text
Song et al. "City-on-Web: Real-Time Neural Rendering of Large-Scale Scenes on the Web." Proceedings of the European Conference on Computer Vision (ECCV), 2024. doi:10.1007/978-3-031-72970-6_22Markdown
[Song et al. "City-on-Web: Real-Time Neural Rendering of Large-Scale Scenes on the Web." Proceedings of the European Conference on Computer Vision (ECCV), 2024.](https://mlanthology.org/eccv/2024/song2024eccv-cityonweb/) doi:10.1007/978-3-031-72970-6_22BibTeX
@inproceedings{song2024eccv-cityonweb,
title = {{City-on-Web: Real-Time Neural Rendering of Large-Scale Scenes on the Web}},
author = {Song, Kaiwen and Zeng, Xiaoyi and Ren, Chenqu and Zhang, Juyong},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
year = {2024},
doi = {10.1007/978-3-031-72970-6_22},
url = {https://mlanthology.org/eccv/2024/song2024eccv-cityonweb/}
}