Neural Parametric Gaussians for Monocular Non-Rigid Object Reconstruction

Comparison on an Unbiased4D Sequence. Figure 1. We present Neural Parametric Gaussians (NPGs), a method for monocular non-rigid reconstruction of objects. a) Our method enables to produce high quality reconstructions in easy settings like the object-level D-NeRF scenes while b) also being able to handle challenging monocular settings much better than previous work through strong parametric low-rank regularization.