RetinaGS: Scalable Training for Dense Scene Rendering with Billion-Scale 3D Gaussians

• Main Authors: Li, Bingling, Chen, Shengyi, Wang, Luchao, Liao, Kaimin, Yan, Sijie, Xiong, Yuanjun
• Format: Journal Article
• Language: English
• Published: 17-06-2024
• Subjects: Computer Science - Computer Vision and Pattern Recognition; Computer Science - Graphics
• DOI: 10.48550/arxiv.2406.11836

In this work, we explore the possibility of training high-parameter 3D
Gaussian splatting (3DGS) models on large-scale, high-resolution datasets. We
design a general model parallel training method for 3DGS, named RetinaGS, which
uses a proper rendering equation and can be applied to any scene and arbitrary
distribution of Gaussian primitives. It enables us to explore the scaling
behavior of 3DGS in terms of primitive numbers and training resolutions that
were difficult to explore before and surpass previous state-of-the-art
reconstruction quality. We observe a clear positive trend of increasing visual
quality when increasing primitive numbers with our method. We also demonstrate
the first attempt at training a 3DGS model with more than one billion
primitives on the full MatrixCity dataset that attains a promising visual
quality.