解决复杂光照与遮挡下的高效高保真三维重建问题
NexusSplats: Efficient 3D Gaussian Splatting in the Wild
- 分层光照解耦+结构感知遮挡处理，提升重建精度
- 参数减少65.4%，重建速度提升2.7倍，效果领先
- 适合真实场景重建，尤其光照多变、遮挡复杂的环境
真实世界无结构场景的逼真三维重建仍面临复杂光照变化和瞬时遮挡的挑战。基于神经辐射场（NeRF）和3D高斯点云（3DGS）的方法在光照解耦效率和结构无关的遮挡处理方面表现不佳。为此，我们提出NexusSplats，一种面向复杂光照与遮挡条件的高效高保真三维场景重建方法。该方法采用分层光照解耦策略，实现集中式外观学习，有效解耦多变的光照条件；同时设计结构感知遮挡处理机制，建立3D与2D结构间的关联，实现细粒度遮挡建模。实验表明，NexusSplats在渲染质量上达到当前最优水平，总参数量减少65.4%，重建速度提升2.7倍。
原文摘要 · Abstract (English)
Photorealistic 3D reconstruction of unstructured real-world scenes remains challenging due to complex illumination variations and transient occlusions. Existing methods based on Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) struggle with inefficient light decoupling and structure-agnostic occlusion handling. To address these limitations, we propose NexusSplats, an approach tailored for efficient and high-fidelity 3D scene reconstruction under complex lighting and occlusion conditions. In particular, NexusSplats leverages a hierarchical light decoupling strategy that performs centralized appearance learning, efficiently and effectively decoupling varying lighting conditions. Furthermore, a structure-aware occlusion handling mechanism is developed, establishing a nexus between 3D and 2D structures for fine-grained occlusion handling. Experimental results demonstrate that NexusSplats achieves state-of-the-art rendering quality and reduces the number of total parameters by 65.4\%, leading to 2.7$\times$ faster reconstruction.
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。