3DGS-LM：利用Levenberg-Marquardt加速高斯泼溅优化
3DGS-LM: Faster Gaussian-Splatting Optimization with Levenberg-Marquardt
AI总结：
本文提出3DGS-LM，用定制Levenberg-Marquardt优化器替代ADAM，并通过CUDA缓存中间梯度高效计算Jacobian-向量乘积，在保持重建质量的同时使3DGS优化速度提升20%。
摘要：
我们提出了3DGS-LM，这是一种新方法，通过用定制的Levenberg-Marquardt（LM）替代其ADAM优化器来加速3D高斯泼溅（3DGS）的重建。现有方法通过减少高斯数量或改进可微光栅化器的实现来缩短优化时间。然而，它们仍然依赖ADAM优化器在数千次迭代中拟合场景的高斯参数，这可能需要长达一小时。为此，我们将优化器改为与3DGS可微光栅化器协同运行的LM。为了实现高效的GPU并行化，我们提出了一种用于中间梯度的缓存数据结构，使我们能够在自定义CUDA内核中高效地计算Jacobian-向量乘积。在每次LM迭代中，我们使用这些内核从多个图像子集计算更新方向，并以加权平均的方式将它们组合起来。总体而言，我们的方法比原始3DGS快20%，同时获得相同的重建质量。我们的优化也与其他加速3DGS的方法无关，因此与普通3DGS相比，可以实现更快的加速。
英文摘要：
We present 3DGS-LM, a new method that accelerates the reconstruction of 3D Gaussian Splatting (3DGS) by replacing its ADAM optimizer with a tailored Levenberg-Marquardt (LM). Existing methods reduce the optimization time by decreasing the number of Gaussians or by improving the implementation of the differentiable rasterizer. However, they still rely on the ADAM optimizer to fit Gaussian parameters of a scene in thousands of iterations, which can take up to an hour. To this end, we change the optimizer to LM that runs in conjunction with the 3DGS differentiable rasterizer. For efficient GPU parallization, we propose a caching data structure for intermediate gradients that allows us to efficiently calculate Jacobian-vector products in custom CUDA kernels. In every LM iteration, we calculate update directions from multiple image subsets using these kernels and combine them in a weighted mean. Overall, our method is 20% faster than the original 3DGS while obtaining the same reconstruction quality. Our optimization is also agnostic to other methods that acclerate 3DGS, thus enabling even faster speedups compared to vanilla 3DGS.
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。
