LGDWT-GS: Local and Global Discrete Wavelet-Regularized 3D Gaussian Splatting for Sparse-View Scene Reconstruction

TL;DR

This paper introduces LGDWT-GS, a novel 3D reconstruction method that combines local and global wavelet regularization to improve detail preservation and stability in sparse-view scenarios, supported by a new multispectral dataset and benchmarking tools.

Contribution

It presents a new wavelet-regularized 3D Gaussian Splatting approach, along with a multispectral dataset and benchmarking package for few-shot 3D reconstruction evaluation.

Findings

Achieves sharper and more stable 3D reconstructions

Demonstrates spectral consistency across different plant species

Outperforms existing baseline methods in experiments

Abstract

We propose a new method for few-shot 3D reconstruction that integrates global and local frequency regularization to stabilize geometry and preserve fine details under sparse-view conditions, addressing a key limitation of existing 3D Gaussian Splatting (3DGS) models. We also introduce a new multispectral greenhouse dataset containing four spectral bands captured from diverse plant species under controlled conditions. Alongside the dataset, we release an open-source benchmarking package that defines standardized few-shot reconstruction protocols for evaluating 3DGS-based methods. Experiments on our multispectral dataset, as well as standard benchmarks, demonstrate that the proposed method achieves sharper, more stable, and spectrally consistent reconstructions than existing baselines. The dataset and code for this work are publicly available