We train dynamic neural radiance fields to predict eventstreams from novel viewpoints and timestamps of a given scene. We share the code for data generation of simulated and real data, as well as code ...
This project proposes a novel strategy utilizing local importance sampling, denoted as L-NeRF. Contrary to traditional NeRF sampling that spans the entire ray, L-NeRF excludes low-weight, uniformly ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback