通过多尺度波浪分解提升图像3D重建精度
Micro-macro Wavelet-based Gaussian Splatting for 3D Reconstruction from Unconstrained Images
- 分层处理全局与细节特征，融合多尺度信息增强表示
- 在多个数据集上实现领先渲染效果，显著改善外观建模
- 适合需要高保真3D重建的视觉算法研究者
从无约束图像集合进行3D重建面临外观差异大、瞬时遮挡等问题。本文提出微-宏波浪分解高斯点阵（MW-GS），将场景表示解耦为全局、精细和固有成分。方法包含两项创新：微-宏投影使高斯点能跨尺度捕捉特征图中的多样化细节；基于小波的采样利用频域信息优化特征表示，显著提升外观建模能力。同时引入分层残差融合网络实现特征无缝集成。大量实验表明，MW-GS在多个基准上达到当前最优渲染性能。
原文摘要 · Abstract (English)
3D reconstruction from unconstrained image collections presents substantial challenges due to varying appearances and transient occlusions. In this paper, we introduce Micro-macro Wavelet-based Gaussian Splatting (MW-GS), a novel approach designed to enhance 3D reconstruction by disentangling scene representations into global, refined, and intrinsic components. The proposed method features two key innovations: Micro-macro Projection, which allows Gaussian points to capture details from feature maps across multiple scales with enhanced diversity; and Wavelet-based Sampling, which leverages frequency domain information to refine feature representations and significantly improve the modeling of scene appearances. Additionally, we incorporate a Hierarchical Residual Fusion Network to seamlessly integrate these features. Extensive experiments demonstrate that MW-GS delivers state-of-the-art rendering performance, surpassing existing methods.
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。