CVJan 23

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

arXiv:2601.17185v11 citationsh-index: 21Has Code
Originality Incremental advance
AI Analysis

This work addresses a key limitation in 3D Gaussian Splatting for sparse-view scene reconstruction, particularly in multispectral domains like greenhouse monitoring, though it appears incremental with a focus on regularization and dataset introduction.

The paper tackles the problem of few-shot 3D reconstruction under sparse-view conditions by integrating global and local frequency regularization into 3D Gaussian Splatting, resulting in sharper, more stable, and spectrally consistent reconstructions compared to existing baselines.

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

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes