Mitigating Motion Blur in Neural Radiance Fields with Events and Frames

arXiv:2403.19780v1 Announce Type: new
Abstract: Neural Radiance Fields (NeRFs) have shown great potential in novel view synthesis. However, they struggle to render sharp images when the data used for training is affected by motion blur. On the other hand, event cameras excel in dynamic scenes as they measure brightness changes with microsecond resolution and are thus only marginally affected by blur. Recent methods attempt to enhance NeRF reconstructions under camera motion by fusing frames and events. However, they face challenges …

abstract arxiv cameras cs.cv data dynamic event events excel fields however images neural radiance fields novel struggle synthesis training type view