Laplacian Frequency Hierarchies for Efficient 3D Gaussian Splatting Training
Yixiong Yang, Sisheng Zhang, Qingsong Yan, Shaohuai Shi et autres
A key bottleneck in 3D Gaussian Splatting training is the continual growth of Gaussian primitives, which increases optimization cost and slows convergence, especially at high resolutions. We propose Laplacian Frequency Hierarchies, a simple yet efficient 3DGS scheme that combines Laplacian image decomposition …
0 citations
arXiv (Cornell University)