GSTA: Efficient Training Scheme with Siestaed Gaussians for Monocular 3D Scene Reconstruction
Year: 2026
Type: conference-paper
Abstract: Gaussian Splatting (GS) is a popular approach for 3D reconstruction, mostly due to its ability to converge reasonably fast, faithfully represent the scene and render (novel) views in a fast fashion. However, it suffers from large storage and memory requirements, and its training speed still lags behind the hash-grid based radiance field approaches (e.g. Instant-NGP), which makes it especially difficult to deploy them in practical use cases. In this paper, we propose GSta that dynamically identifies Gaussians that have converged well during training, based on their positional and color gradient norms. By forcing such Gaussians into a siesta and stopping their updates (freezing) during training, we improve training speed with competitive accuracy compared to state of the art. We also propose an early stopping mechanism based on the PSNR values computed on a subset of training images. Combined with other improvements, such as integrating a learning rate scheduler, GSta achieves an improved Pareto front in convergence speed, memory and storage requirements, while preserving quality. We also show that GSta can complement other efficiency-improving methods and once combined GSta achieves up to 5× faster training, 16× smaller disk size compared to vanilla GS, while having comparable accuracy and consuming only half the peak memory.
Institution: Samsung Electronics (South Korea)
Language: English
Subfield: Computational Mechanics
Field: Engineering
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4416531046
FWCI:
Cites:
Cited by:
Related to: