EvDNeRF: Reconstructing Event Data with Dynamic Neural Radiance Fields

Anish Bhattacharya    Ratnesh Madaan    Fernando Cladera    Sai Vemprala    Rogerio Bonatti     Kostas Daniilidis, Ashish Kapoor    Vijay Kumar    Nikolai Matni    Jayesh Gupta

We present a pipeline to generate event-based datasets and train dynamic NeRF models in a self supervised fashion from event-based data; by reconstructing events from novel viewpoints and times, EvDNeRF can then act as an event camera simulator for the given scene.

This site is a work in progress -- links will be provided for the paper, code, and datasets very soon.