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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Song, Kaiwen, Zeng, Xiaoyi, Ren, Chenqu, Zhang, Juyong
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916185345359872
author Song, Kaiwen
Zeng, Xiaoyi
Ren, Chenqu
Zhang, Juyong
author_facet Song, Kaiwen
Zeng, Xiaoyi
Ren, Chenqu
Zhang, Juyong
contents 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 combined with dynamic loading/unloading of resources to significantly reduce memory demands. Our system achieves real-time rendering of large-scale scenes at approximately 32FPS with RTX 3060 GPU on the web and maintains rendering quality comparable to the current state-of-the-art novel view synthesis methods.
format Preprint
id arxiv_https___arxiv_org_abs_2312_16457
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle City-on-Web: Real-time Neural Rendering of Large-scale Scenes on the Web
Song, Kaiwen
Zeng, Xiaoyi
Ren, Chenqu
Zhang, Juyong
Computer Vision and Pattern Recognition
Graphics
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 combined with dynamic loading/unloading of resources to significantly reduce memory demands. Our system achieves real-time rendering of large-scale scenes at approximately 32FPS with RTX 3060 GPU on the web and maintains rendering quality comparable to the current state-of-the-art novel view synthesis methods.
title City-on-Web: Real-time Neural Rendering of Large-scale Scenes on the Web
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2312.16457