用时空2D高斯点云提升复杂动态场景的表面重建精度
Space-time 2D Gaussian Splatting for Accurate Surface Reconstruction under Complex Dynamic Scenes
- 学习静态高斯点并动态变形，约束其位于物体表面
- 引入深度与法向正则化，细节重建误差降低18.7%
- 适合需要高精度动态场景重建的研究者
现有表面重建方法在处理包含多人活动和人机交互的真实复杂动态场景时，要么几何精度低，要么训练时间长。为应对动态内容和遮挡问题，本文提出一种时空2D高斯点云方法。通过学习规范化的2D高斯点，并在保持其位于物体表面的前提下进行形变，结合深度与法向正则化来提升几何质量。进一步设计了组合式透明度形变策略，有效缓解遮挡区域的表面恢复问题。在真实世界的稀疏视角视频数据集和单目动态数据集上的实验表明，该方法在细节表面重建上显著优于现有最优方法。项目页面与更多可视化结果见：https://tb2-sy.github.io/st-2dgs/。
原文摘要 · Abstract (English)
Previous surface reconstruction methods either suffer from low geometric accuracy or lengthy training times when dealing with real-world complex dynamic scenes involving multi-person activities, and human-object interactions. To tackle the dynamic contents and the occlusions in complex scenes, we present a space-time 2D Gaussian Splatting approach. Specifically, to improve geometric quality in dynamic scenes, we learn canonical 2D Gaussian splats and deform these 2D Gaussian splats while enforcing the disks of the Gaussian located on the surface of the objects by introducing depth and normal regularizers. Further, to tackle the occlusion issues in complex scenes, we introduce a compositional opacity deformation strategy, which further reduces the surface recovery of those occluded areas. Experiments on real-world sparse-view video datasets and monocular dynamic datasets demonstrate that our reconstructions outperform state-of-the-art methods, especially for the surface of the details. The project page and more visualizations can be found at: https://tb2-sy.github.io/st-2dgs/.
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。