用多层小波变换调控3D高斯点云密度，减少显存占用。
Learnable Multi-level Discrete Wavelet Transforms for 3D Gaussian Splatting Frequency Modulation
- 通过递归分解低频子带构建多级训练监督
- 仅用一个缩放参数即可完成频率调制，降低计算开销
- 在保持渲染质量前提下显著减少高斯点数量，适合资源受限场景
3D高斯点阵（3DGS）已成为新视角合成的强大方法。然而，训练过程中为重建更精细的场景细节，高斯基元数量会急剧增长，导致内存与存储成本上升。近期的粗到精策略通过调节真实图像的频率内容来控制高斯增长。例如，AutoOpti3DGS采用可学习的离散小波变换（DWT）实现数据自适应频率调制。但其调制深度受限于单层DWT，且联合优化小波正则化与3D重建会引入梯度竞争，导致高斯点过度稠密化。本文提出基于多层DWT的频率调制框架，通过递归分解低频子带，构建更深层的训练课程，在早期训练中提供逐步粗化的监督，持续降低高斯点数量。此外，我们证明只需一个缩放参数即可完成调制，无需学习完整的2抽头高通滤波器。在标准基准上的实验结果表明，该方法在保持竞争力渲染质量的同时进一步减少了高斯点数量。
原文摘要 · Abstract (English)
3D Gaussian Splatting (3DGS) has emerged as a powerful approach for novel view synthesis. However, the number of Gaussian primitives often grows substantially during training as finer scene details are reconstructed, leading to increased memory and storage costs. Recent coarse-to-fine strategies regulate Gaussian growth by modulating the frequency content of the ground-truth images. In particular, AutoOpti3DGS employs the learnable Discrete Wavelet Transform (DWT) to enable data-adaptive frequency modulation. Nevertheless, its modulation depth is limited by the 1-level DWT, and jointly optimizing wavelet regularization with 3D reconstruction introduces gradient competition that promotes excessive Gaussian densification. In this paper, we propose a multi-level DWT-based frequency modulation framework for 3DGS. By recursively decomposing the low-frequency subband, we construct a deeper curriculum that provides progressively coarser supervision during early training, consistently reducing Gaussian counts. Furthermore, we show that the modulation can be performed using only a single scaling parameter, rather than learning the full 2-tap high-pass filter. Experimental results on standard benchmarks demonstrate that our method further reduces Gaussian counts while maintaining competitive rendering quality.
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。