期刊
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022)
卷 -, 期 -, 页码 5491-5500出版社
IEEE COMPUTER SOC
DOI: 10.1109/CVPR52688.2022.00542
关键词
-
资金
- CONIX Research Center - DARPA
- Google research faculty award
- ONR [N00014-20-1-2497, N00014-18-1-2833]
- NSF CPS award [1931853]
- DARPA Assured Autonomy program [FA8750-18-C-0101]
- NSF GRFP
- Div Of Civil, Mechanical, & Manufact Inn
- Directorate For Engineering [1931853] Funding Source: National Science Foundation
We introduce Plenoxels, a system for photorealistic view synthesis using a sparse 3D grid representation with spherical harmonics. This representation can be optimized without neural components and achieves a two orders of magnitude faster speed compared to Neural Radiance Fields on benchmark tasks while maintaining visual quality.
We introduce Plenoxels (plenoptic voxels), a system for photorealistic view synthesis. Plenoxels represent a scene as a sparse 3D grid with spherical harmonics. This representation can be optimized from calibrated images via gradient methods and regularization without any neural components. On standard, benchmark tasks, Plenoxels are optimized two orders of magnitude faster than Neural Radiance Fields with no loss in visual quality. For video and code, please see https://alexyu.net/plenoxels.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据