gsplat：一個用於高斯點塗探的開源程式庫

gsplat: An Open-Source Library for Gaussian Splatting

September 10, 2024

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

cs.AI

摘要

gsplat是一個開源庫，旨在用於訓練和開發高斯點降方法。它具有一個前端，具有與PyTorch庫兼容的Python綁定，以及具有高度優化的CUDA核心的後端。gsplat提供了許多功能，可增強高斯點降模型的優化，包括針對速度、內存和收斂時間的優化改進。實驗結果表明，gsplat實現了比原始實現更少達10%的訓練時間和4倍的內存。gsplat已應用於多個研究項目中，並在GitHub上積極維護。源代碼可在https://github.com/nerfstudio-project/gsplat 下載，採用Apache License 2.0。我們歡迎來自開源社區的貢獻。

English

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.