An Exploration of Neural Radiance Field Scene Reconstruction: Synthetic, Real-world and Dynamic Scenes

Traditional NeRF approaches can reconstruct both synthetic This project presents an exploration into 3D scene reconstruction and real-world scenes and new methods like Instant of synthetic and real-world scenes using Neural Neural Graphics Primitives [5] significantly speed up the Radiance Field (NeRF) approaches. We primarily take NeRF training process, however, these methods are limited advantage of the reduction in training and rendering time to scenes with static Objects. D-NeRF (Dynamic NeRF [7]) of neural graphic primitives multi-resolution hash encoding, extends traditional NeRF with time conditioning making it to reconstruct static video game scenes and real-world possible to reconstruct scenes with dynamic objects, however, scenes-comparing and observing reconstruction detail and the implementation of D-NeRF was limited to synthetic limitations. Additionally, we explore dynamic scene reconstruction scenes where ground truth camera parameters exist. Our goal using Neural Radiance Fields for Dynamic is to extend the implementation of D-NeRF to reconstruct Scenes(D-NeRF). Finally, we extend the implementation of real-world scenes with dynamic objects like dancing people. D-NeRF, originally constrained to handle synthetic scenes to also handle real-world dynamic scenes.