Micro-macro Wavelet-based Gaussian Splatting for 3D Reconstruction from Unconstrained Images
Yihui Li, Chengxin Lv, Hongyu Yang, Di Huang
Abstract
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.
BibTeX
@article{Li_Lv_Yang_Huang_2025, title={Micro-macro Wavelet-based Gaussian Splatting for 3D Reconstruction from Unconstrained Images}, volume={39}, url={https://ojs.aaai.org/index.php/AAAI/article/view/32536}, DOI={10.1609/aaai.v39i5.32536}, abstractNote={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.}, number={5}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Li, Yihui and Lv, Chengxin and Yang, Hongyu and Huang, Di}, year={2025}, month={Apr.}, pages={5057-5065} }