From Coarse to Fine: Learnable Discrete Wavelet Transforms for Efficient 3D Gaussian Splatting

TL;DR

AutoOpti3DGS introduces a learnable wavelet transform framework for 3D Gaussian Splatting that reduces Gaussian proliferation, improves efficiency, and maintains high visual fidelity in novel view synthesis.

Contribution

It proposes a novel wavelet-based, coarse-to-fine training framework that automatically restrains Gaussian growth in 3D Gaussian Splatting without sacrificing quality.

Findings

Requires only one hyper-parameter for filter learning.

Produces sparser scene representations.

Enhances compatibility with memory-constrained hardware.

Abstract

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.