Robust Dynamic Radiance Fields

https://robust-dynrf.github.io/ Figure 1 . Robust space-time synthesis from dynamic monocular videos. Our method takes a casually captured video as input and reconstructs the camera trajectory and dynamic radiance fields. Conventional SfM system such as COLMAP fails to recover camera poses even when using ground truth motion masks. As a result, existing dynamic radiance field methods that require accurate pose estimation do not work on these challenging dynamic scenes. Our work tackles this robustness problem and showcases high-fidelity dynamic view synthesis results on a wide variety of videos.