用动态感知优化高斯点云，从日常视频重建静态场景
DAS3R: Dynamics-Aware Gaussian Splatting for Static Scene Reconstruction
- 将运动掩码与高斯点云结合，动态感知优化背景重建
- 在DAVIS和Sintel数据集上比现有方法提升超2 dB的PSNR
- 无需相机位姿或SLAM点云，适合复杂动态场景
我们提出一种新框架，从日常视频中分解场景并重建静态背景。通过整合训练好的运动掩码，并将静态场景建模为具有动态感知优化的高斯点云，该方法在背景重建精度上优于以往工作。所提方法命名为DAS3R（Dynamics-Aware Gaussian Splatting for Static Scene Reconstruction）。相较于现有方法，DAS3R在复杂运动场景下更鲁棒，可处理动态物体占据大量画面的视频，且无需相机位姿输入或基于SLAM的点云数据。我们在DAVIS和Sintel数据集上对比了近期无干扰方法，DAS3R在性能和鲁棒性上均有提升，PSNR提升超过2 dB。项目主页可通过\url{https://kai422.github.io/DAS3R/}访问。
原文摘要 · Abstract (English)
We propose a novel framework for scene decomposition and static background reconstruction from everyday videos. By integrating the trained motion masks and modeling the static scene as Gaussian splats with dynamics-aware optimization, our method achieves more accurate background reconstruction results than previous works. Our proposed method is termed DAS3R, an abbreviation for Dynamics-Aware Gaussian Splatting for Static Scene Reconstruction. Compared to existing methods, DAS3R is more robust in complex motion scenarios, capable of handling videos where dynamic objects occupy a significant portion of the scene, and does not require camera pose inputs or point cloud data from SLAM-based methods. We compared DAS3R against recent distractor-free approaches on the DAVIS and Sintel datasets; DAS3R demonstrates enhanced performance and robustness with a margin of more than 2 dB in PSNR. The project's webpage can be accessed via \url{https://kai422.github.io/DAS3R/}
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。