Dynamic EventNeRF: Reconstructing General Dynamic Scenes from Multi-view RGB and Event Streams

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Rudnev, Viktor, Fox, Gereon, Elgharib, Mohamed, Theobalt, Christian, Golyanik, Vladislav
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909692225126400
author Rudnev, Viktor
Fox, Gereon
Elgharib, Mohamed
Theobalt, Christian
Golyanik, Vladislav
author_facet Rudnev, Viktor
Fox, Gereon
Elgharib, Mohamed
Theobalt, Christian
Golyanik, Vladislav
contents Volumetric reconstruction of dynamic scenes is an important problem in computer vision. It is especially challenging in poor lighting and with fast motion. This is partly due to limitations of RGB cameras: To capture frames under low lighting, the exposure time needs to be increased, which leads to more motion blur. In contrast, event cameras, which record changes in pixel brightness asynchronously, are much less dependent on lighting, making them more suitable for recording fast motion. We hence propose the first method to spatiotemporally reconstruct a scene from sparse multi-view event streams and sparse RGB frames. We train a sequence of cross-faded time-conditioned NeRF models, one per short recording segment. The individual segments are supervised with a set of event- and RGB-based losses and sparse-view regularisation. We assemble a real-world multi-view camera rig with six static event cameras around the object and record a benchmark multi-view event stream dataset of challenging motions. Our work outperforms RGB-based baselines, producing state-of-the-art results, and opens up the topic of multi-view event-based reconstruction as a new path for fast scene capture beyond RGB cameras. The code and the data are released at https://4dqv.mpi-inf.mpg.de/DynEventNeRF/
format Preprint
id arxiv_https___arxiv_org_abs_2412_06770
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Dynamic EventNeRF: Reconstructing General Dynamic Scenes from Multi-view RGB and Event Streams
Rudnev, Viktor
Fox, Gereon
Elgharib, Mohamed
Theobalt, Christian
Golyanik, Vladislav
Computer Vision and Pattern Recognition
Volumetric reconstruction of dynamic scenes is an important problem in computer vision. It is especially challenging in poor lighting and with fast motion. This is partly due to limitations of RGB cameras: To capture frames under low lighting, the exposure time needs to be increased, which leads to more motion blur. In contrast, event cameras, which record changes in pixel brightness asynchronously, are much less dependent on lighting, making them more suitable for recording fast motion. We hence propose the first method to spatiotemporally reconstruct a scene from sparse multi-view event streams and sparse RGB frames. We train a sequence of cross-faded time-conditioned NeRF models, one per short recording segment. The individual segments are supervised with a set of event- and RGB-based losses and sparse-view regularisation. We assemble a real-world multi-view camera rig with six static event cameras around the object and record a benchmark multi-view event stream dataset of challenging motions. Our work outperforms RGB-based baselines, producing state-of-the-art results, and opens up the topic of multi-view event-based reconstruction as a new path for fast scene capture beyond RGB cameras. The code and the data are released at https://4dqv.mpi-inf.mpg.de/DynEventNeRF/
title Dynamic EventNeRF: Reconstructing General Dynamic Scenes from Multi-view RGB and Event Streams
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2412.06770