ParticleNeRF: A Particle-Based Encoding for Online Neural Radiance Fields in Dynamic Scenes

Neural Radiance Fields (NeRFs) learn implicit representations of - typically static - environments from images. Our paper extends NeRFs to handle dynamic scenes in an online fashion. We propose ParticleNeRF that adapts to changes in the geometry of the environment as they occur, learning a new up-to-date representation every 350ms. ParticleNeRF can represent the current state of dynamic environments with much higher fidelity compared to other NeRF frameworks. To achieve this, we introduce a new particle-based parametric encoding, which allows the intermediate NeRF features -- now coupled to particles in space - to move with the dynamic geometry. This is possible by backpropagating the photometric reconstruction loss into the position of the particles. The position gradients are interpreted as particle velocities and integrated into positions using a position-based dynamics (PBS) physics system. Introducing PBS into the NeRF formulation allows us to add collision constraints to the particle motion and creates future opportunities to add other movement priors into the system, such as rigid and deformable body constraints. Videos can be found at https://sites.google.com/view/particlenerf.