BIGS: Bimanual Category-agnostic Interaction Reconstruction from Monocular Videos via 3D Gaussian Splatting

Novel view video (e.g., egocentric view) Output Novel hand / object / camera pose Animatable hands and objects time Reconstructed hand-object interaction Figure 1. Our approach reconstructs 3D Gaussians of bimanual category-agnostic interactions from a monocular video, where the two hands interact with an unknown object. Even with limited observations, our method reliably builds the 3D Gaussians in this scenario and once 3D Gaussians are built, our method can be used to render new videos with novel poses of hand, object and camera (i.e., view).