BLiRF: Bandlimited Radiance Fields for Dynamic Scene Modeling

Figure 1: We address the problem of recovering the 3D structure of a dynamic scene given sparse RGB views from a monocular, moving camera. The figure shows a comparison between novel views of a challenging scene with long-range dynamics as synthesized by our proposed model and a competitive baseline. As illustrated, our model is able to capture fine details better and accurately localize the motion compared to NR-NeRF [36]. We attribute the superior performance of our model to efficient factorization of time and space dynamics that enable incorporating well-defined spatio-temporal priors, leading to better recovery of complex dynamics.