用LM优化器提速3D高斯溅射，重建快20%且质量不变。
3DGS-LM: Faster Gaussian-Splatting Optimization with Levenberg-Marquardt
- 改用定制化莱文伯格-马尔夸特优化器替代ADAM。
- 在相同质量下比原版3DGS快20%，单次优化耗时显著降低。
- 兼容其他加速方法，适合需要快速3D重建的研究者。
我们提出3DGS-LM，通过将3D高斯溅射（3DGS）的ADAM优化器替换为定制化的莱文伯格-马尔夸特（LM）算法，加速场景重建过程。现有方法通过减少高斯数量或优化可微渲染器实现加速，但仍依赖ADAM在数千次迭代中拟合高斯参数，耗时可达一小时。为此，我们将LM优化器与3DGS可微渲染器结合，设计了一种用于中间梯度的缓存数据结构，支持在自定义CUDA内核中高效计算雅可比-向量乘积。每次LM迭代中，利用多个图像子集并行计算更新方向，并以加权平均合并。整体方法比原版3DGS快20%，且重建质量相当。该优化对其他加速3DGS的方法具有兼容性，可进一步提升速度。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。