Paper Info
Title
Fast Image Reconstruction with an Event Camera
Abstract
Event cameras are powerful new sensors able to capture high dynamic range with microsecond temporal resolution and no motion blur. Their strength is detecting brightness changes (called events) rather than capturing direct brightness images; however, algorithms can be used to convert events into usable image representations for applications such as classification. Previous works rely on hand-crafted spatial and temporal smoothing techniques to reconstruct images from events. State-of-the-art video reconstruction has recently been achieved using neural networks that are large (10M parameters) and computationally expensive, requiring 30ms for a forward-pass at 640 × 480 resolution on a modern GPU. We propose a novel neural network architecture for video reconstruction from events that is smaller (38k vs. 10M parameters) and faster (10ms vs. 30ms) than state-of-the-art with minimal impact to performance.
Year
DOI
Venue
2020
10.1109/WACV45572.2020.9093366
2020 IEEE Winter Conference on Applications of Computer Vision (WACV)
Keywords
DocType
ISSN
temporal smoothing techniques,video reconstruction,image reconstruction,event camera,microsecond temporal resolution,brightness changes,direct brightness images,image representations,neural network architecture
Conference
2472-6737
ISBN
Citations 
PageRank 
978-1-7281-6554-7
2
0.36
References 
Authors
15
6
Name
Order
Citations
PageRank
Cedric Scheerlinck1162.93
Henri Rebecq2964.76
Daniel Gehrig395.18
Nick Barnes457768.68
Robert E. Mahony51691162.83
Davide Scaramuzza62704154.51