I3DGS：从多个维度改进 3D Gaussian Splatting
I3DGS: Improve 3D Gaussian Splatting from Multiple Dimensions
AI总结：
本文提出 I3DS 评估改进方案，从多维度开展两千余项实验分析 3D Gaussian Splatting 的训练效率，并引入 95/94 进制压缩机制，经微调实现显著性能提升且代码开源。
摘要：
3D Gaussian Splatting 是一种用于三维视图合成的新颖方法，相比传统神经渲染技术，它能够获得隐式神经学习的渲染结果，同时保持更高清晰度和快速渲染速度。然而，对于实际应用而言，要在 3D Gaussian Splatting 上实现足够快的效率仍然困难。为解决这一问题，我们提出 I3DS，这是一个综合性的模型性能改进评估方案与实验测试。我们从原始 3D Gaussian Splatting 的多个重要层级或维度出发，进行了两千多种各类实验，以测试所选的不同项目和组件如何影响 3D Gaussian Splatting 模型的训练效率。本文将分享大量关于如何改进训练、性能以及模型不同项目所造成影响的有意义经验和方法。文中提出了一种特殊但常见的、基于 95 进制的整数压缩，以及基于 94 进制并采用 ASCII 编码和解码机制的浮点数压缩。许多真实有效的实验、测试结果或现象将被记录。经过一系列合理微调后，I3DS 相比先前方案能够获得出色的性能提升。项目代码已开源。
英文摘要：
3D Gaussian Splatting is a novel method for 3D view synthesis, which can gain an implicit neural learning rendering result than the traditional neural rendering technology but keep the more high-definition fast rendering speed. But it is still difficult to achieve a fast enough efficiency on 3D Gaussian Splatting for the practical applications. To Address this issue, we propose the I3DS, a synthetic model performance improvement evaluation solution and experiments test. From multiple and important levels or dimensions of the original 3D Gaussian Splatting, we made more than two thousand various kinds of experiments to test how the selected different items and components can make an impact on the training efficiency of the 3D Gaussian Splatting model. In this paper, we will share abundant and meaningful experiences and methods about how to improve the training, performance and the impacts caused by different items of the model. A special but normal Integer compression in base 95 and a floating-point compression in base 94 with ASCII encoding and decoding mechanism is presented. Many real and effective experiments and test results or phenomena will be recorded. After a series of reasonable fine-tuning, I3DS can gain excellent performance improvements than the previous one. The project code is available as open source.
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。
