gsplat: An Open-Source Library for Gaussian Splatting
This is an incremental improvement for researchers and developers working with Gaussian Splatting methods, offering better computational efficiency.
The authors developed gsplat, an open-source library for Gaussian Splatting that provides optimized CUDA kernels and PyTorch bindings, achieving up to 10% faster training and 4x less memory usage compared to the original implementation.
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.