paper-with-me

홈 › Papers

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

2023-12-27 · Kaiwen Song, Xiaoyi Zeng, Chenqu Ren, Juyong Zhang

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.

📄 PDF Abstract BibTeX arXiv:2312.16457

Code (1)

USTC3DV/MERFStudio 공식 구현 jax

Tasks

3D Scene ReconstructionGPUManagementNeural RenderingNovel View Synthesis

Similar Papers 제목 키워드 기반

CityGaussian: Real-time High-quality Large-Scale Scene Rendering with Gaussians

2024-04-01 · Yang Liu, He Guan, Chuanchen Luo, Lue Fan 외

The advancement of real-time 3D scene reconstruction and novel view synthesis has been significantly propelled by 3D Gaussian Splatting (3DGS). However, effectively training large-scale 3DGS and rendering it in real-time…

3DGS3D Scene ReconstructionNovel View Synthesis

MatrixCity: A Large-scale City Dataset for City-scale Neural Rendering and Beyond

2023-09-28 · ICCV 2023 1 · Yixuan Li, Lihan Jiang, Linning Xu, Yuanbo Xiangli 외

Neural radiance fields (NeRF) and its subsequent variants have led to remarkable progress in neural rendering. While most of recent neural rendering works focus on objects and small-scale scenes, developing neural render…

NeRFNeural Rendering

NeRFusion: Fusing Radiance Fields for Large-Scale Scene Reconstruction

2022-03-21 · CVPR 2022 1 · Xiaoshuai Zhang, Sai Bi, Kalyan Sunkavalli, Hao Su 외

While NeRF has shown great success for neural reconstruction and rendering, its limited MLP capacity and long per-scene optimization times make it challenging to model large-scale indoor scenes. In contrast, classical 3D…

3D ReconstructionNeRF

CityGo: Lightweight Urban Modeling and Rendering with Proxy Buildings and Residual Gaussians

2025-05-27 · Weihang Liu, Yuhui Zhong, Yuke Li, Xi Chen 외

Accurate and efficient modeling of large-scale urban scenes is critical for applications such as AR navigation, UAV based inspection, and smart city digital twins. While aerial imagery offers broad coverage and complemen…

3DGS

LODGE: Level-of-Detail Large-Scale Gaussian Splatting with Efficient Rendering

2025-05-29 · Jonas Kulhanek, Marie-Julie Rakotosaona, Fabian Manhardt, Christina Tsalicoglou 외

In this work, we present a novel level-of-detail (LOD) method for 3D Gaussian Splatting that enables real-time rendering of large-scale scenes on memory-constrained devices. Our approach introduces a hierarchical LOD rep…

3DGSGPUNeRF