arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.06765cs.CV
收藏

gsplat:一个用于高斯泼溅(Gaussian Splatting)的开源库

gsplat: An Open-Source Library for Gaussian Splatting

UC Berkeley(加州大学伯克利分校);Aalto University(阿尔托大学);ShanghaiTech University(上海科技大学);SpectacularAI;Amazon(亚马逊公司);Luma AI

Vickie Ye, Ruilong Li, Justin Kerr, Matias Turkulainen, Brent Yi, Zhuoyang Pan, Otto Seiskari, Jianbo Ye, Jeffrey Hu, Matthew Tancik, Angjoo Kanazawa

AI总结:

本研究推出开源库gsplat,前端兼容PyTorch、后端搭载优化CUDA内核,可提升高斯泼溅模型的速度、内存与收敛表现,训练时间最多降10%、内存最多省4倍,已用于多个科研项目且在GitHub活跃维护。

摘要:

gsplat是一个专为训练和开发Gaussian Splatting(高斯泼溅)方法设计的开源库。它的前端具备与PyTorch库兼容的Python绑定,后端则搭载了高度优化的CUDA内核。gsplat提供了众多可增强Gaussian Splatting模型优化效果的特性,包括在速度、内存和收敛时长方面的优化改进。实验结果表明,与原始实现相比,gsplat的训练时间最多缩短10%,内存占用最多降低4倍。该库已被应用于多个研究项目,目前在GitHub上处于活跃维护状态,源代码以Apache License 2.0协议发布于https://github.com/nerfstudio-project/gsplat,我们欢迎开源社区贡献代码。

英文摘要:

gsplat is an open-source library designed for training and developing Gaussian Splatting methods. It features a front-end with Python bindings compatible with the PyTorch library and a back-end with highly optimized CUDA kernels. gsplat offers numerous features that enhance the optimization of Gaussian Splatting models, which include optimization improvements for speed, memory, and convergence times. Experimental results demonstrate that gsplat achieves up to 10% less training time and 4x less memory than the original implementation. Utilized in several research projects, gsplat is actively maintained on GitHub. Source code is available at https://github.com/nerfstudio-project/gsplat under Apache License 2.0. We welcome contributions from the open-source community.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑