Zimu Liao, Siyan Chen, Rong Fu, Yi Wang, Zhongling Su, Hao Luo, Linning Xu, Bo Dai, Hengjie Li, Zhilin Pei, Xingcheng Zhang
{"title":"Fisheye-GS: Lightweight and Extensible Gaussian Splatting Module for Fisheye Cameras","authors":"Zimu Liao, Siyan Chen, Rong Fu, Yi Wang, Zhongling Su, Hao Luo, Linning Xu, Bo Dai, Hengjie Li, Zhilin Pei, Xingcheng Zhang","doi":"arxiv-2409.04751","DOIUrl":null,"url":null,"abstract":"Recently, 3D Gaussian Splatting (3DGS) has garnered attention for its high\nfidelity and real-time rendering. However, adapting 3DGS to different camera\nmodels, particularly fisheye lenses, poses challenges due to the unique 3D to\n2D projection calculation. Additionally, there are inefficiencies in the\ntile-based splatting, especially for the extreme curvature and wide field of\nview of fisheye lenses, which are crucial for its broader real-life\napplications. To tackle these challenges, we introduce Fisheye-GS.This\ninnovative method recalculates the projection transformation and its gradients\nfor fisheye cameras. Our approach can be seamlessly integrated as a module into\nother efficient 3D rendering methods, emphasizing its extensibility,\nlightweight nature, and modular design. Since we only modified the projection\ncomponent, it can also be easily adapted for use with different camera models.\nCompared to methods that train after undistortion, our approach demonstrates a\nclear improvement in visual quality.","PeriodicalId":501174,"journal":{"name":"arXiv - CS - Graphics","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Graphics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.04751","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
Recently, 3D Gaussian Splatting (3DGS) has garnered attention for its high
fidelity and real-time rendering. However, adapting 3DGS to different camera
models, particularly fisheye lenses, poses challenges due to the unique 3D to
2D projection calculation. Additionally, there are inefficiencies in the
tile-based splatting, especially for the extreme curvature and wide field of
view of fisheye lenses, which are crucial for its broader real-life
applications. To tackle these challenges, we introduce Fisheye-GS.This
innovative method recalculates the projection transformation and its gradients
for fisheye cameras. Our approach can be seamlessly integrated as a module into
other efficient 3D rendering methods, emphasizing its extensibility,
lightweight nature, and modular design. Since we only modified the projection
component, it can also be easily adapted for use with different camera models.
Compared to methods that train after undistortion, our approach demonstrates a
clear improvement in visual quality.