通过频域正则化提升稀疏视角下3D高斯泼溅的稳定性与细节保留能力
LGDWT-GS: Local and Global Discrete Wavelet-Regularized 3D Gaussian Splatting for Sparse-View Scene Reconstruction
- 融合全局与局部频域正则化，增强稀疏视图下的几何稳定性
- 在多光谱数据集上实现更锐利、更一致的重建结果，显著优于基线方法
- 适用于植物表型分析等需要高精度稀疏重建的科研场景
我们提出一种新型少样本3D重建方法，通过引入全局与局部频域正则化，在稀疏视角条件下稳定几何结构并保留精细细节，解决了现有3D高斯泼溅（3DGS）模型的关键缺陷。同时，我们构建了一个新的多光谱温室数据集，包含四种光谱波段，由多种植物物种在受控环境下采集。伴随该数据集，我们发布一个开源基准测试工具包，定义了标准化的少样本重建评估协议，用于评估基于3DGS的方法。在该多光谱数据集及标准基准上的实验表明，所提方法在重建清晰度、稳定性与光谱一致性方面均优于现有基线。本研究的数据集与代码已公开。
原文摘要 · Abstract (English)
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
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。