Learn to See by Events: Color Frame Synthesis from Event and RGB Cameras

Stefano Pini, Guido Borghi, Roberto Vezzani, Roberto Vezzani

2020

Abstract

Event cameras are biologically-inspired sensors that gather the temporal evolution of the scene. They capture pixel-wise brightness variations and output a corresponding stream of asynchronous events. Despite having multiple advantages with respect to traditional cameras, their use is partially prevented by the limited applicability of traditional data processing and vision algorithms. To this aim, we present a framework which exploits the output stream of event cameras to synthesize RGB frames, relying on an initial or a periodic set of color key-frames and the sequence of intermediate events. Differently from existing work, we propose a deep learning-based frame synthesis method, consisting of an adversarial architecture combined with a recurrent module. Qualitative results and quantitative per-pixel, perceptual, and semantic evaluation on four public datasets confirm the quality of the synthesized images.

Download


Paper Citation


in Harvard Style

Pini S., Borghi G. and Vezzani R. (2020). Learn to See by Events: Color Frame Synthesis from Event and RGB Cameras. In Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 4: VISAPP; ISBN 978-989-758-402-2, SciTePress, pages 37-47. DOI: 10.5220/0008934700370047


in Bibtex Style

@conference{visapp20,
author={Stefano Pini and Guido Borghi and Roberto Vezzani},
title={Learn to See by Events: Color Frame Synthesis from Event and RGB Cameras},
booktitle={Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 4: VISAPP},
year={2020},
pages={37-47},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0008934700370047},
isbn={978-989-758-402-2},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 4: VISAPP
TI - Learn to See by Events: Color Frame Synthesis from Event and RGB Cameras
SN - 978-989-758-402-2
AU - Pini S.
AU - Borghi G.
AU - Vezzani R.
PY - 2020
SP - 37
EP - 47
DO - 10.5220/0008934700370047
PB - SciTePress