用新方法从随意拍摄视频中重建动态3D场景，效果更准更稳。
RoDyGS: Robust Dynamic Gaussian Splatting for Casual Videos
- 分离静态与动态物体，结合时空约束提升几何合理性。
- 在自定义基准上实现比现有方法更优的动态新视角生成效果。
- 适合做视频重建、虚拟拍摄的开发者和研究者参考。
从随意拍摄的单目视频中进行4D重建面临固有的动态三维几何模糊问题。为此，我们提出鲁棒动态高斯点云渲染（RoDyGS），可从随意拍摄的单目视频中重建动态场景表示。该方法显式分离静态与动态场景元素，并引入时空正则化以保证几何物理合理性及运动时序一致性。此外，我们构建了综合性基准Kubric-MRig，包含丰富的相机与物体运动，以及同步多视角采集，弥补了以往基准的不足。实验表明，RoDyGS显著优于现有无位姿动态新视角生成方法，在渲染质量上也达到与现有无位姿静态新视角生成方法相当的水平。
原文摘要 · Abstract (English)
4D reconstruction from casually captured monocular videos is challenging due to inherent ambiguity in reconstructing dynamic 3D geometry. To address this challenge, we introduce Robust Dynamic Gaussian Splatting (RoDyGS), a method that reconstructs dynamic scene representation from casual monocular videos. RoDyGS explicitly separates static and dynamic scene elements, and applies spatiotemporal regularization to enforce physically plausible geometry and temporally consistent motion. Furthermore, we propose a comprehensive benchmark, Kubric-MRig, which provides extensive camera and object motion along with simultaneous multi-view capture, features that are absent in previous benchmarks. Experiments demonstrate that RoDyGS significantly outperforms previous pose-free dynamic novel view synthesis approaches and achieves competitive rendering quality compared to existing pose-free static novel view synthesis approaches. Our proejct page is available at https://rodygs.github.io
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。