通过可学习小波变换，让3D高斯点云训练更省内存且保持画质。
From Coarse to Fine: Learnable Discrete Wavelet Transforms for Efficient 3D Gaussian Splatting
- 用可学习的小波变换从粗到细逐步生成高斯点，延迟冗余细节创建。
- 仅需一个学习率超参数，训练后场景表示更稀疏，节省内存带宽。
- 适合资源受限设备，兼容现有高效3D高斯框架，无需复杂调整。
3D高斯点云渲染在新视角合成中表现出色，训练与渲染快速，但高斯原语数量持续增长，导致内存和带宽压力。本文提出AutoOpti3DGS，一种训练时自动抑制高斯膨胀的框架，不牺牲视觉质量。核心思路是将输入图像通过一系列可学习的前向与逆向离散小波变换，其中低通滤波器固定，高通滤波器可学习且初始化为零，并引入辅助正交性损失逐步激活高频成分。这一由粗到细的小波驱动过程延缓了冗余细粒度高斯的生成，使3DGS优先捕捉全局结构，仅在必要时细化细节。大量实验表明，AutoOpti3DGS仅需单一学习率超参数，可无缝集成至现有高效3DGS框架，始终生成更稀疏的场景表示，更适用于内存或存储受限硬件。
原文摘要 · Abstract (English)
3D Gaussian Splatting has emerged as a powerful approach in novel view synthesis, delivering rapid training and rendering but at the cost of an ever-growing set of Gaussian primitives that strains memory and bandwidth. We introduce AutoOpti3DGS, a training-time framework that automatically restrains Gaussian proliferation without sacrificing visual fidelity. The key idea is to feed the input images to a sequence of learnable Forward and Inverse Discrete Wavelet Transforms, where low-pass filters are kept fixed, high-pass filters are learnable and initialized to zero, and an auxiliary orthogonality loss gradually activates fine frequencies. This wavelet-driven, coarse-to-fine process delays the formation of redundant fine Gaussians, allowing 3DGS to capture global structure first and refine detail only when necessary. Through extensive experiments, AutoOpti3DGS requires just a single filter learning-rate hyper-parameter, integrates seamlessly with existing efficient 3DGS frameworks, and consistently produces sparser scene representations more compatible with memory or storage-constrained hardware.
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。