Structure from motion and Tiny NeRF

Reconstruct a 3D scene and simultaneously obtain the camera poses of a monocular camera w.r.t. the given scene. This procedure is known as Structure from Motion (SfM). As the name suggests, you are creating the entire rigid structure from a set of images with different view points (or equivalently a camera in motion). This project also implemented a tiny nerf model to reconstruct the view from a unkonwn position using deep learning method